© 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. 15-LLAMASCOPE-RES-131K
    11. 87415
    Prev
    Next
    INDEX
    Explanations

    instances of the word "filed."

    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
    a
    -0.07
    .FontStyle
    -0.06
    ICODE
    -0.06
    abo
    -0.06
     Gregory
    -0.06
    entiful
    -0.06
    izzle
    -0.06
    cdb
    -0.06
     Daly
    -0.06
    bench
    -0.06
    POSITIVE LOGITS
    rios
    0.08
    丹
    0.07
    ogg
    0.07
    Äįer
    0.07
    sob
    0.06
    ëŁ
    0.06
    oref
    0.06
    ÑĥÑĢÑĥ
    0.06
    Misc
    0.06
    chner
    0.06
    Activations Density 0.001%

    No Known Activations