© 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. 125423
    Prev
    Next
    INDEX
    Explanations

    indicators of literary contributions

    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
    ovice
    -0.08
    lotte
    -0.06
    ë£
    -0.06
    SystemService
    -0.06
     audiences
    -0.06
    ServiceProvider
    -0.06
     Wikipedia
    -0.06
    ·¸
    -0.06
    BG
    -0.06
    ÄĻ
    -0.06
    POSITIVE LOGITS
    ubar
    0.07
    licit
    0.07
    rig
    0.07
     anthology
    0.07
     Anth
    0.07
     anth
    0.07
     Prompt
    0.07
     addCriterion
    0.07
    Anth
    0.07
     flash
    0.07
    Activations Density 0.037%

    No Known Activations