© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 108284
    Prev
    Next
    INDEX
    Explanations

    structure or formatting in scientific documents

    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
    oretical
    -0.06
    fid
    -0.06
    elor
    -0.05
    ofs
    -0.05
     explanation
    -0.05
    ala
    -0.05
    istr
    -0.05
    fav
    -0.05
    ble
    -0.05
     pattern
    -0.05
    POSITIVE LOGITS
    umlu
    0.08
    ·
    0.07
    ýt
    0.07
    ÐĽÐĺ
    0.07
     Laden
    0.07
     sıras
    0.07
     %%↵
    0.07
    ’ÑĹ
    0.07
    \xa
    0.07
    oÅĻ
    0.07
    Activations Density 0.003%

    No Known Activations