© 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. 63103
    Prev
    Next
    INDEX
    Explanations

    terms and declarations related to APIs and programming constructs

    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
    abay
    -0.07
    ostat
    -0.06
    steller
    -0.06
    illow
    -0.06
    dehy
    -0.06
    udur
    -0.06
    èĭ
    -0.06
    311
    -0.06
    mise
    -0.06
    "nil
    -0.06
    POSITIVE LOGITS
    ãĥ¼ãĥ©
    0.07
    §
    0.07
    аÑĢод
    0.06
    anchor
    0.06
    ovna
    0.06
    ¨
    0.06
    /browse
    0.06
    елик
    0.06
    ï¼
    0.06
    #echo
    0.06
    Activations Density 0.001%

    No Known Activations