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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8-LLAMASCOPE-RES-32K
    6. 6649
    Prev
    Next
    INDEX
    Explanations

    references to Venice and its geographical or cultural features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etch
    -0.15
    VILLE
    -0.15
    inci
    -0.15
    iyon
    -0.14
    ienia
    -0.14
    age
    -0.14
     æº
    -0.13
    pler
    -0.13
    _defs
    -0.13
     fulfillment
    -0.13
    POSITIVE LOGITS
     Fav
    0.15
     hass
    0.15
    mpar
    0.14
     Sac
    0.14
     Holiday
    0.14
    ÌĨ
    0.14
    oz
    0.14
    .throw
    0.13
    ably
    0.13
    ariat
    0.13
    Activations Density 0.014%

    No Known Activations