© 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. 22-LLAMASCOPE-RES-131K
    11. 4163
    Prev
    Next
    INDEX
    Explanations

    terms associated with bodily movements and physical conditions

    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
    ers
    -0.09
    ERS
    -0.08
    yg
    -0.08
    ies
    -0.08
    rophe
    -0.08
    yla
    -0.07
    eus
    -0.07
    erver
    -0.07
    bilt
    -0.07
    vale
    -0.07
    POSITIVE LOGITS
    ting
    0.27
    ging
    0.20
    bing
    0.20
    ming
    0.19
    ning
    0.18
    TING
    0.18
    ged
    0.16
    MING
    0.16
    ter
    0.15
    med
    0.15
    Activations Density 0.073%

    No Known Activations