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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-LLAMASCOPE-RES-131K
    6. 96054
    Prev
    Next
    INDEX
    Explanations

    details related to geographic locations and jurisdictions

    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
    utex
    -0.07
     str
    -0.07
    isbn
    -0.07
    ekl
    -0.07
    gaard
    -0.06
    entai
    -0.06
    ãĥĥãĥī
    -0.06
    unas
    -0.06
    ifik
    -0.06
    кеÑĤ
    -0.06
    POSITIVE LOGITS
    anners
    0.07
     Belt
    0.06
    /Area
    0.06
    eken
    0.06
    iese
    0.06
    .pathname
    0.06
    permanent
    0.06
    214
    0.06
    atis
    0.06
     ÑĤÑĢÑĥ
    0.06
    Activations Density 0.024%

    No Known Activations