© 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 EvalsExportsAPI 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. 60972
    Prev
    Next
    INDEX
    Explanations

    certain ratings or timestamps related to content

    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
    ISP
    -0.07
    vik
    -0.06
    ovo
    -0.06
     Minor
    -0.06
    Dados
    -0.06
    927
    -0.06
     Corona
    -0.06
    Indented
    -0.06
     onto
    -0.06
    bury
    -0.06
    POSITIVE LOGITS
     ÙĨب
    0.07
    LEAN
    0.06
    eventId
    0.06
    .qq
    0.06
    luž
    0.06
    REM
    0.06
     Artikel
    0.06
     Adresse
    0.06
    lean
    0.06
    doll
    0.06
    Activations Density 0.001%

    No Known Activations