© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 104191
    Prev
    Next
    INDEX
    Explanations

    conjunctions and references to legislative assemblies or gatherings

    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
    roperty
    -0.08
    ahoo
    -0.07
    _LIBRARY
    -0.07
    edor
    -0.07
    ìĿ´ìĬ¤
    -0.07
    enberg
    -0.07
    Ãĭ
    -0.06
    ovu
    -0.06
    quelle
    -0.06
     sabah
    -0.06
    POSITIVE LOGITS
    erken
    0.07
     yourselves
    0.07
    gem
    0.06
    éĻ¢
    0.06
     tôi
    0.06
     basically
    0.06
    .='
    0.06
    ãģĨãģ¡
    0.06
    htub
    0.06
    گاÙĩ
    0.06
    Activations Density 0.000%

    No Known Activations