Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 30-LLAMASCOPE-RES-32K
    6. 8441
    Prev
    Next
    INDEX
    Explanations

    descriptions of unusual or unexpected sightings or encounters, particularly related to mysterious objects or creatures.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @trainjumperx

    descriptions of unusual or anomalous phenomena, particularly mysterious objects or creatures.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @trainjumperx

    intense or dramatic events, particularly explosions or significant occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ollar
    -0.15
    _fold
    -0.15
    ĥn
    -0.14
    271
    -0.14
    .inject
    -0.14
    éľ²åĩº
    -0.13
    aktu
    -0.13
    ŀ
    -0.13
    ÑĢовод
    -0.13
    ecko
    -0.13
    POSITIVE LOGITS
     craft
    0.27
     object
    0.25
    craft
    0.24
     Craft
    0.23
     Object
    0.22
    Craft
    0.22
    -object
    0.22
     stationary
    0.21
     crafts
    0.21
    Object
    0.20
    Activations Density 0.040%

    No Known Activations