© 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. 91873
    Prev
    Next
    INDEX
    Explanations

    content related to advice, guidance, and informational resources

    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
    rox
    -0.07
    acker
    -0.06
    .lambda
    -0.06
    uyu
    -0.06
    CTR
    -0.06
     vaz
    -0.06
     Courier
    -0.06
    aga
    -0.06
    olan
    -0.06
    æĭħ
    -0.06
    POSITIVE LOGITS
    327
    0.07
    frei
    0.07
     about
    0.06
    842
    0.06
    icensing
    0.06
    artz
    0.06
    484
    0.06
     vá»ģ
    0.06
    afil
    0.06
     from
    0.06
    Activations Density 0.025%

    No Known Activations