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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-LLAMASCOPE-RES-32K
    6. 15836
    Prev
    Next
    INDEX
    Explanations

    specific nouns or terms that indicate a location or identifier

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     çĤ
    -0.18
     meslek
    -0.17
    ÑĢÑĥн
    -0.16
    578
    -0.15
    olini
    -0.15
    anj
    -0.15
    olah
    -0.14
    ibu
    -0.14
     nomine
    -0.14
    rup
    -0.14
    POSITIVE LOGITS
    aign
    0.17
    alker
    0.16
    ,
    0.16
     pick
    0.15
     in
    0.15
     surrounded
    0.15
     ex
    0.15
     straight
    0.15
     besides
    0.15
    Toolkit
    0.14
    Activations Density 0.011%

    No Known Activations