© 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. 30770
    Prev
    Next
    INDEX
    Explanations

    words related to physical activities and actions

    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
    ings
    -0.09
    ingly
    -0.08
    Ing
    -0.07
    ÂŃing
    -0.07
     ing
    -0.07
     ling
    -0.07
    INGS
    -0.06
    sys
    -0.06
     Ing
    -0.06
    ING
    -0.06
    POSITIVE LOGITS
    redient
    0.07
    еÑģÑĤо
    0.07
    est
    0.07
    ynch
    0.07
    Æ°á»Ľ
    0.06
    ests
    0.06
    /from
    0.06
    estion
    0.06
    rieve
    0.06
    967
    0.06
    Activations Density 0.073%

    No Known Activations