© 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. 31414
    Prev
    Next
    INDEX
    Explanations

    occurrences of dialogue or interactions between characters

    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
    HttpException
    -0.07
    ï¿¥
    -0.07
    ufs
    -0.07
    нÑĤ
    -0.07
     tostring
    -0.07
     zbo
    -0.07
     authDomain
    -0.06
     Abbey
    -0.06
    .consumer
    -0.06
    .Sdk
    -0.06
    POSITIVE LOGITS
    iser
    0.07
    à¹Īà¸Ńà¸Ļ
    0.07
     Fo
    0.06
     olup
    0.06
    -Series
    0.06
    -ID
    0.05
     fo
    0.05
     readers
    0.05
     Patreon
    0.05
    ium
    0.05
    Activations Density 0.008%

    No Known Activations