© 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. 80492
    Prev
    Next
    INDEX
    Explanations

    expressions of personal achievement and potential

    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
    rick
    -0.07
    emax
    -0.07
    ÏĢÎŃ
    -0.07
    OnChange
    -0.06
    Dll
    -0.06
    rita
    -0.06
    .Skip
    -0.06
    -UA
    -0.06
    ague
    -0.06
    売
    -0.06
    POSITIVE LOGITS
     can
    0.07
    eties
    0.06
    URRED
    0.06
     otherwise
    0.06
     Residence
    0.06
     Braun
    0.06
    .tap
    0.06
     Fet
    0.06
    694
    0.06
    grese
    0.06
    Activations Density 0.038%

    No Known Activations