© 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. 80287
    Prev
    Next
    INDEX
    Explanations

    references to programming constructs or methods

    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
    esti
    -0.08
    essaging
    -0.07
    iaux
    -0.07
    lÃŃ
    -0.07
    utters
    -0.07
    agma
    -0.07
    ataire
    -0.07
    lesi
    -0.06
    etooth
    -0.06
    andon
    -0.06
    POSITIVE LOGITS
    IRST
    0.07
    fen
    0.06
    ISON
    0.06
    ãģ¦
    0.06
    ourn
    0.06
     latter
    0.06
    .EN
    0.06
    ICES
    0.06
    furt
    0.06
    KK
    0.05
    Activations Density 0.000%

    No Known Activations