© 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. 15-LLAMASCOPE-RES-131K
    11. 27030
    Prev
    Next
    INDEX
    Explanations

    references to decision-making and process completion

    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
    ailable
    -0.07
     Cop
    -0.07
    csr
    -0.06
    /Branch
    -0.06
    Ymd
    -0.06
    rompt
    -0.06
    reh
    -0.06
    iba
    -0.06
    æݨèĸ¦
    -0.06
    .criteria
    -0.06
    POSITIVE LOGITS
     finish
    0.11
     finishes
    0.10
     finishing
    0.10
     finished
    0.09
    finish
    0.09
     Finish
    0.08
     completion
    0.08
    Finish
    0.08
     Finished
    0.08
     Completion
    0.08
    Activations Density 0.053%

    No Known Activations