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. 6-LLAMASCOPE-RES-32K
    6. 21505
    Prev
    Next
    INDEX
    Explanations

    references to menus and menu-related terms in dining contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    129
    -0.16
    ç
    -0.15
     Hedge
    -0.14
    /is
    -0.14
    422
    -0.14
     Q
    -0.14
    ais
    -0.14
     fle
    -0.14
     majority
    -0.13
    anium
    -0.13
    POSITIVE LOGITS
    ìĸ¼
    0.17
    gebung
    0.16
    \Blueprint
    0.15
    ãĥĬãĥ«
    0.15
    inaire
    0.15
    \Builder
    0.15
    .setVerticalGroup
    0.15
    ulfilled
    0.14
    ascript
    0.14
    HeaderCode
    0.14
    Activations Density 0.012%

    No Known Activations