© 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. 83296
    Prev
    Next
    INDEX
    Explanations

    actions and movements that suggest physical interactions or changes in position

    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
     Peace
    -0.07
     peace
    -0.06
    ĥ
    -0.06
     knobs
    -0.06
    é¡ĺ
    -0.06
    elter
    -0.06
    ãĥĸãĥ©
    -0.06
    rieve
    -0.06
     drag
    -0.06
     пеÑĢе
    -0.06
    POSITIVE LOGITS
     sitting
    0.10
     rowspan
    0.08
     Sitting
    0.08
     seated
    0.08
     sits
    0.08
     sit
    0.07
    seat
    0.07
    åĿIJ
    0.07
    -seat
    0.07
    Seat
    0.07
    Activations Density 0.010%

    No Known Activations