© 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. 84319
    Prev
    Next
    INDEX
    Explanations

    references to Wikipedia and related concepts like documentation and product safety

    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
    lä
    -0.06
    artz
    -0.06
    RAINT
    -0.06
    incinn
    -0.06
    御
    -0.06
    affer
    -0.06
    idunt
    -0.06
    amin
    -0.06
    acc
    -0.06
    pth
    -0.06
    POSITIVE LOGITS
     Laur
    0.06
    \Twig
    0.06
     GENERIC
    0.06
    iesen
    0.06
    ormap
    0.06
    è¥
    0.06
    eba
    0.06
    ÄĽk
    0.05
     Bale
    0.05
    ĩ
    0.05
    Activations Density 0.000%

    No Known Activations