© 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. 9-LLAMASCOPE-RES-131K
    11. 94307
    Prev
    Next
    INDEX
    Explanations

    references to competitive sports events or competitions

    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
    zung
    -0.07
    xy
    -0.06
    ane
    -0.06
    zar
    -0.06
    ocado
    -0.06
    arlo
    -0.06
    ahn
    -0.06
     odp
    -0.06
    ,
    -0.05
    aho
    -0.05
    POSITIVE LOGITS
     ì¡
    0.07
    .synthetic
    0.07
    atatype
    0.07
     abstract
    0.07
    ìĬ¤íĭ°
    0.06
     consc
    0.06
    ADF
    0.06
    lernen
    0.06
     cá»Ń
    0.06
    OOK
    0.06
    Activations Density 0.000%

    No Known Activations