© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 77896
    Prev
    Next
    INDEX
    Explanations

    references to specific body parts or anatomical terms

    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
    alom
    -0.08
    mitt
    -0.07
    ضÙħ
    -0.07
    ril
    -0.07
    raj
    -0.07
    ipur
    -0.07
    wav
    -0.07
    esti
    -0.07
    chwitz
    -0.07
    ÑĥÑĤи
    -0.06
    POSITIVE LOGITS
    formance
    0.07
    stal
    0.07
    ptide
    0.07
    oples
    0.07
    ity
    0.06
    acock
    0.06
    sterol
    0.06
    ermint
    0.06
    joy
    0.06
    FORMANCE
    0.06
    Activations Density 0.015%

    No Known Activations