© 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. 108674
    Prev
    Next
    INDEX
    Explanations

    terminology related to performances and events

    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
    .office
    -0.07
    errer
    -0.07
    ruba
    -0.07
    ocene
    -0.07
    bih
    -0.07
    .Office
    -0.07
     Rae
    -0.06
     UFC
    -0.06
    ombo
    -0.06
    äºĮ人
    -0.06
    POSITIVE LOGITS
     marching
    0.07
    usch
    0.07
     Winds
    0.07
     sectional
    0.07
    éŀ
    0.07
     Campo
    0.06
    arris
    0.06
     Unlimited
    0.06
     xsi
    0.06
     Corrections
    0.06
    Activations Density 0.022%

    No Known Activations