© 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. 103698
    Prev
    Next
    INDEX
    Explanations

    proper nouns and references to specific events or characters

    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
    ilden
    -0.06
    .apps
    -0.06
    foy
    -0.06
    uden
    -0.06
    ToObject
    -0.05
    alse
    -0.05
     Alternative
    -0.05
     заг
    -0.05
    997
    -0.05
     Stad
    -0.05
    POSITIVE LOGITS
     similarly
    0.12
     next
    0.10
     ÑĤоже
    0.09
    (next
    0.09
    next
    0.09
    imilar
    0.09
     ebenfalls
    0.09
    _next
    0.09
     similar
    0.08
    similar
    0.08
    Activations Density 0.020%

    No Known Activations