© 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. 80619
    Prev
    Next
    INDEX
    Explanations

    aspects related to numerical data or statistics

    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
    s
    -0.19
    Ùĩ
    -0.10
    in
    -0.09
    и
    -0.07
    -0.07
    ipt
    -0.07
    à¤ķ
    -0.07
    sian
    -0.07
    n
    -0.07
    otope
    -0.06
    POSITIVE LOGITS
    likle
    0.07
    ļ
    0.07
    OVE
    0.06
    ?type
    0.06
    GetType
    0.06
    -INF
    0.06
    agli
    0.06
     *,↵
    0.06
    /ajax
    0.06
    Monad
    0.06
    Activations Density 0.076%

    No Known Activations