© 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. 38928
    Prev
    Next
    INDEX
    Explanations

    phrases indicating possession or completion

    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
    alink
    -0.08
    .scalablytyped
    -0.08
     PATCH
    -0.08
    大åħ¨
    -0.08
    onec
    -0.07
    uiltin
    -0.07
    antas
    -0.07
    jÃŃt
    -0.07
    las
    -0.07
    Patch
    -0.07
    POSITIVE LOGITS
     tried
    0.08
     separ
    0.07
     also
    0.06
     trying
    0.06
     tries
    0.06
     thoroughly
    0.06
     sop
    0.06
     try
    0.06
     L
    0.06
     Dah
    0.06
    Activations Density 0.008%

    No Known Activations