© 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. 124728
    Prev
    Next
    INDEX
    Explanations

    evaluations of music and trends in popular culture

    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
    reeze
    -0.08
    лами
    -0.07
    lag
    -0.07
     Prize
    -0.07
     generations
    -0.07
    боÑĤ
    -0.07
    pty
    -0.07
    ascar
    -0.07
    thur
    -0.07
    lags
    -0.07
    POSITIVE LOGITS
    année
    0.07
    202
    0.07
    201
    0.07
     year
    0.07
    ä»Ĭå¹´
    0.07
     Year
    0.07
    Year
    0.07
     Jahres
    0.06
    /ex
    0.06
     année
    0.06
    Activations Density 0.031%

    No Known Activations