© 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. 117946
    Prev
    Next
    INDEX
    Explanations

    classifications of substances or items, particularly pertaining to safety and health standards

    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
    uš
    -0.08
    erli
    -0.08
    219
    -0.07
    anko
    -0.07
    ancellable
    -0.07
    506
    -0.07
    clone
    -0.07
    essel
    -0.07
    fur
    -0.07
    LATED
    -0.07
    POSITIVE LOGITS
    /type
    0.08
    ì§ľ
    0.06
    /Form
    0.06
    .tm
    0.06
     level
    0.06
    âĢ³
    0.06
    åŀĭ
    0.06
    edic
    0.06
    asmus
    0.06
    bis
    0.06
    Activations Density 0.037%

    No Known Activations