© 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. 53832
    Prev
    Next
    INDEX
    Explanations

    phrases indicating movement or action

    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
    ko
    -0.07
     Robbins
    -0.06
    up
    -0.06
    udeau
    -0.06
     resort
    -0.06
    ater
    -0.06
    spar
    -0.06
    k
    -0.06
    deaux
    -0.06
    dw
    -0.05
    POSITIVE LOGITS
    ì´Į
    0.08
    ázev
    0.08
    CppType
    0.07
    ritel
    0.07
    [$_
    0.07
    .LayoutStyle
    0.07
    ashire
    0.07
    Ïģθ
    0.07
     stall
    0.07
    odÃŃ
    0.07
    Activations Density 0.006%

    No Known Activations