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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 56479
    Prev
    Next
    INDEX
    Explanations

    elements related to physical movement and bodily awareness

    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
    ych
    -0.06
     former
    -0.06
     ag
    -0.06
    u
    -0.06
    \\\
    -0.06
    idel
    -0.05
    inos
    -0.05
    âĢİ
    -0.05
     Barr
    -0.05
    dash
    -0.05
    POSITIVE LOGITS
    Ñĩки
    0.08
    #ab
    0.08
    ãĥ©ãĤ¤ãĥ³
    0.08
    ór
    0.07
    erialized
    0.07
    (#)
    0.07
    #af
    0.07
    amax
    0.07
    .Encode
    0.07
    orge
    0.07
    Activations Density 0.009%

    No Known Activations