© 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. 28742
    Prev
    Next
    INDEX
    Explanations

    references to lunch-related activities or events

    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
     CLR
    -0.07
    opus
    -0.07
    oser
    -0.07
    .za
    -0.07
    .nc
    -0.07
    rena
    -0.06
    jsc
    -0.06
     Accent
    -0.06
    bis
    -0.06
    udded
    -0.06
    POSITIVE LOGITS
    time
    0.10
    ãĥ§
    0.08
    ing
    0.08
    -time
    0.08
    ette
    0.08
    enburg
    0.08
    esModule
    0.07
    eson
    0.07
    ificent
    0.07
    (es
    0.07
    Activations Density 0.004%

    No Known Activations