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. 31-LLAMASCOPE-RES-131K
    6. 44025
    Prev
    Next
    INDEX
    Explanations

    references to classic cars and their history in motorsport

    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
    $route
    -0.07
    imei
    -0.07
    éĥ½å¸Ĥ
    -0.07
    uren
    -0.06
    èι
    -0.06
    :convert
    -0.06
    .mapbox
    -0.06
     Oversight
    -0.06
    //{{
    -0.06
    ãĤıãģĽ
    -0.06
    POSITIVE LOGITS
     Historic
    0.10
     Festival
    0.09
     Histor
    0.09
     Good
    0.09
     histor
    0.09
     historic
    0.09
     Retro
    0.09
     vintage
    0.09
     Classic
    0.08
     Vintage
    0.08
    Activations Density 0.021%

    No Known Activations