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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 22-LLAMASCOPE-RES-131K
    6. 5463
    Prev
    Next
    INDEX
    Explanations

    references to legal disclaimers and site usage conditions

    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
    lear
    -0.07
    belt
    -0.06
     Comple
    -0.06
    pire
    -0.06
    Comple
    -0.06
     signific
    -0.06
    ÑĢÑĥд
    -0.06
    ÑĢел
    -0.06
    ooth
    -0.06
     Belt
    -0.06
    POSITIVE LOGITS
    urger
    0.07
    ç¯
    0.07
    anno
    0.07
    اÙĦÙĬا
    0.07
    ctor
    0.07
     Hamp
    0.07
    ismet
    0.06
    ÑĥÑĩа
    0.06
    anka
    0.06
    sis
    0.06
    Activations Density 0.000%

    No Known Activations