© 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. 54033
    Prev
    Next
    INDEX
    Explanations

    references to vehicles, particularly cars and their features

    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
    Ø°
    -0.06
     Eb
    -0.06
     ano
    -0.06
     amat
    -0.06
    ź
    -0.06
    usto
    -0.06
     Erik
    -0.06
     Incorporated
    -0.06
     Exc
    -0.06
     gente
    -0.06
    POSITIVE LOGITS
    Äĥ
    0.09
     Romanian
    0.08
     Buna
    0.07
     Romania
    0.07
     pentru
    0.07
    buie
    0.07
    .ro
    0.07
     din
    0.07
     despre
    0.07
    azÄĥ
    0.07
    Activations Density 0.018%

    No Known Activations