© 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. 118424
    Prev
    Next
    INDEX
    Explanations

    references to the film industry, particularly individual actors and their roles

    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
     Readers
    -0.07
     readers
    -0.07
    lif
    -0.07
    undry
    -0.07
    SSL
    -0.06
    AccessType
    -0.06
    arf
    -0.06
    WA
    -0.06
    yll
    -0.06
    ancell
    -0.06
    POSITIVE LOGITS
     IMDb
    0.07
    è±Ĩ
    0.07
    ensch
    0.07
     cast
    0.07
     ÑĥÑĩаÑģÑĤи
    0.07
     Credits
    0.07
     è±
    0.07
    untime
    0.06
    .bc
    0.06
     Plot
    0.06
    Activations Density 0.028%

    No Known Activations