Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95940
    Prev
    Next
    INDEX
    Explanations

    references to numerical values or identifiers

    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
    eka
    -0.07
     Hö
    -0.07
    ût
    -0.07
    øy
    -0.07
    füh
    -0.06
     consenting
    -0.06
    ìŀ¡
    -0.06
    ernes
    -0.06
    ÙĪØ²
    -0.06
    elman
    -0.06
    POSITIVE LOGITS
    βά
    0.07
    ewis
    0.06
    skirts
    0.06
    ãĤ·ãĥ£
    0.06
    umba
    0.06
    .heroku
    0.06
    691
    0.06
     Walls
    0.06
    à¥įण
    0.06
    ?p
    0.06
    Activations Density 0.013%

    No Known Activations