© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 120578
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the outcome or impact of decisions and actions

    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
    celed
    -0.07
     Gia
    -0.07
     ÑĤоваÑĢи
    -0.06
    ntag
    -0.06
     Poz
    -0.06
    uide
    -0.06
    ìľĦ
    -0.06
    957
    -0.06
    uda
    -0.06
     Fatal
    -0.06
    POSITIVE LOGITS
    alth
    0.07
    _fds
    0.07
    ialis
    0.06
     Ñģобой
    0.06
    raya
    0.06
    fic
    0.06
    avin
    0.06
    rase
    0.06
    icone
    0.06
     immediate
    0.06
    Activations Density 0.038%

    No Known Activations