© 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. 5919
    Prev
    Next
    INDEX
    Explanations

    references to events or performances

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ec
    -0.06
     McKin
    -0.06
     Skinner
    -0.06
     Ridley
    -0.05
    nan
    -0.05
     stakes
    -0.05
    ÂĢ
    -0.05
    اÛĮع
    -0.05
    asley
    -0.05
     BJ
    -0.05
    POSITIVE LOGITS
    _GPS
    0.07
    IID
    0.07
    andr
    0.07
     Smy
    0.07
     repar
    0.07
    veh
    0.06
     Composite
    0.06
    ugi
    0.06
    ucker
    0.06
    925
    0.06
    Activations Density 0.000%

    No Known Activations