© 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. 76335
    Prev
    Next
    INDEX
    Explanations

    references to acting careers and performances in film and theater

    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
     ÑĩаÑģом
    -0.08
    reh
    -0.08
    elong
    -0.08
    loud
    -0.07
    ovu
    -0.07
    oud
    -0.07
    odata
    -0.07
    åª
    -0.07
    airy
    -0.07
    ologne
    -0.07
    POSITIVE LOGITS
     tiny
    0.07
    YP
    0.06
     neighborhood
    0.06
     small
    0.06
    å°ı
    0.06
     cad
    0.06
     anonymously
    0.06
     violently
    0.06
     Minor
    0.06
     lokale
    0.06
    Activations Density 0.023%

    No Known Activations