© 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. 116689
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to classes, programs, and memberships

    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
    ecast
    -0.07
    rente
    -0.06
    asing
    -0.06
    ụn
    -0.06
    ass
    -0.06
     simple
    -0.06
     Rent
    -0.06
    aison
    -0.06
     worldwide
    -0.06
    insi
    -0.05
    POSITIVE LOGITS
    gee
    0.07
    gger
    0.07
    ropol
    0.07
    _FATAL
    0.07
    PLOY
    0.07
    CORE
    0.07
     ÑĤоб
    0.07
    imei
    0.07
    #:
    0.07
    raya
    0.07
    Activations Density 0.038%

    No Known Activations