© 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. 69387
    Prev
    Next
    INDEX
    Explanations

    references to feeling absurd or ridiculous in social situations

    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
    odel
    -0.06
    ponsive
    -0.06
    dbName
    -0.06
    atta
    -0.06
    olean
    -0.06
    /open
    -0.06
    oro
    -0.06
    represented
    -0.06
    athon
    -0.06
    inen
    -0.06
    POSITIVE LOGITS
     odd
    0.08
     abnormal
    0.08
    INGLE
    0.07
     embarrassing
    0.07
     eccentric
    0.07
    å®Ŀ
    0.07
     credibility
    0.07
    UTH
    0.07
    afari
    0.06
     weird
    0.06
    Activations Density 0.038%

    No Known Activations