© 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. 94642
    Prev
    Next
    INDEX
    Explanations

    names and titles associated with discussions about creativity and personal expression

    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
    tte
    -0.09
    obre
    -0.06
    quin
    -0.06
    ilter
    -0.06
    spath
    -0.06
    bas
    -0.06
    lux
    -0.06
    ãĥ¼ãĥ«ãĥī
    -0.06
    ses
    -0.06
    ื
    -0.06
    POSITIVE LOGITS
    Interview
    0.09
     Interview
    0.09
     interview
    0.08
     interviewer
    0.08
     entrev
    0.08
    chwitz
    0.07
    252
    0.07
    èªĮ
    0.07
    NL
    0.07
    /question
    0.07
    Activations Density 0.006%

    No Known Activations