© 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. 83227
    Prev
    Next
    INDEX
    Explanations

    questions or inquiries about specifics regarding various topics

    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
    oro
    -0.07
    901
    -0.06
    545
    -0.06
    endar
    -0.06
     forg
    -0.06
    rens
    -0.06
     Jo
    -0.06
    148
    -0.06
    ism
    -0.05
    -focus
    -0.05
    POSITIVE LOGITS
     kind
    0.09
     kinds
    0.08
    /how
    0.08
     amount
    0.08
    kind
    0.08
     type
    0.07
     portion
    0.07
     Ñģаме
    0.07
     types
    0.07
    ucid
    0.07
    Activations Density 0.024%

    No Known Activations