© 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. 104317
    Prev
    Next
    INDEX
    Explanations

    references to physical appearance and body types

    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
     Extended
    -0.06
    foot
    -0.06
    uml
    -0.06
     Elevated
    -0.06
    uma
    -0.06
    vue
    -0.06
    ava
    -0.06
     tong
    -0.05
    ood
    -0.05
    Foot
    -0.05
    POSITIVE LOGITS
     lean
    0.09
     physique
    0.09
    çĺ
    0.09
     शर
    0.08
     sculpt
    0.08
     body
    0.08
    mus
    0.08
    arine
    0.08
    .body
    0.08
    licative
    0.08
    Activations Density 0.050%

    No Known Activations