© 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. 1523
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating ability or possibility

    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
     ours
    -0.08
     нами
    -0.07
     ourselves
    -0.07
     nostro
    -0.07
    erner
    -0.07
     our
    -0.06
    zh
    -0.06
    ãĥģãĥ¼ãĥł
    -0.06
    rá
    -0.06
    stra
    -0.06
    POSITIVE LOGITS
     Overse
    0.07
    Äįer
    0.07
    ÅĻeh
    0.06
    kker
    0.06
     inference
    0.06
    argin
    0.06
    umba
    0.06
    ÃŃcia
    0.06
    892
    0.06
    ึà¸ģ
    0.06
    Activations Density 0.020%

    No Known Activations