© 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. 94833
    Prev
    Next
    INDEX
    Explanations

    references to health and safety measures

    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
     favorites
    -0.07
    uki
    -0.06
    ÐĿÐĨ
    -0.06
    favorites
    -0.06
     favor
    -0.06
    uku
    -0.06
     (£
    -0.06
    uzzi
    -0.06
    atta
    -0.06
     favorite
    -0.06
    POSITIVE LOGITS
    strup
    0.08
    atri
    0.07
    itzer
    0.07
    Äįi
    0.07
    asing
    0.07
     DISCLAIM
    0.07
    .opensource
    0.07
    ppv
    0.06
    Ñıк
    0.06
     маÑĤемаÑĤи
    0.06
    Activations Density 0.003%

    No Known Activations