© 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. 78153
    Prev
    Next
    INDEX
    Explanations

    references to the act of biting or being bitten

    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
    λιά
    -0.07
    lund
    -0.07
    ries
    -0.07
    tera
    -0.07
    ãģĦãĤĭ
    -0.07
    loader
    -0.06
    ONGO
    -0.06
    UNET
    -0.06
    agate
    -0.06
    issen
    -0.06
    POSITIVE LOGITS
    umin
    0.09
    ycastle
    0.07
    ables
    0.07
    kowski
    0.07
    ful
    0.06
     bite
    0.06
    iful
    0.06
    å¿ł
    0.06
    packing
    0.06
    åĬĽ
    0.06
    Activations Density 0.006%

    No Known Activations