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. 31-LLAMASCOPE-RES-131K
    6. 11462
    Prev
    Next
    INDEX
    Explanations

    numerical information related to distances and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cz
    -0.06
    odata
    -0.06
     Bench
    -0.06
    wp
    -0.06
    ampa
    -0.06
    Ĭ¶
    -0.06
     Illustrated
    -0.06
    bench
    -0.06
     OST
    -0.06
    insky
    -0.06
    POSITIVE LOGITS
     mi
    0.16
    Âłmi
    0.12
     fi
    0.11
     km
    0.10
    (mi
    0.10
    .mi
    0.10
     MI
    0.09
     min
    0.09
     Mi
    0.08
    _mi
    0.08
    Activations Density 0.006%

    No Known Activations