© 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. 40184
    Prev
    Next
    INDEX
    Explanations

    references to educational organizations and teaching experiences

    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
    idental
    -0.07
     Patreon
    -0.07
    eki
    -0.07
    uliar
    -0.06
    lage
    -0.06
     Amateur
    -0.06
    actus
    -0.06
    æº
    -0.06
    วย
    -0.06
    à¥ģव
    -0.06
    POSITIVE LOGITS
    itez
    0.06
     pairing
    0.06
    /mat
    0.06
     è±
    0.06
     Entry
    0.06
     placement
    0.06
     placements
    0.06
    arrant
    0.06
     ëı
    0.06
    æ¼¢
    0.06
    Activations Density 0.022%

    No Known Activations