© 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. 126470
    Prev
    Next
    INDEX
    Explanations

    elements related to event genres and user interactions in a programming context

    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
    inea
    -0.07
    Äįel
    -0.07
    ãģıãĤĵ
    -0.07
    .remaining
    -0.07
     Synd
    -0.07
    à¸ķำ
    -0.07
    PIP
    -0.07
    fed
    -0.06
    -vars
    -0.06
    ÑĸÑĩна
    -0.06
    POSITIVE LOGITS
    hasMany
    0.08
     relationship
    0.07
     foreign
    0.06
     link
    0.06
     Link
    0.06
    Link
    0.06
    515
    0.06
    ë§ģ
    0.06
     Pil
    0.06
     linking
    0.06
    Activations Density 0.001%

    No Known Activations