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. 43522
    Prev
    Next
    INDEX
    Explanations

    symbols or characters that may represent special notation or formulas

    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
     Covid
    -0.06
     covid
    -0.06
    ='".
    -0.06
    ðŁ
    -0.06
     sulph
    -0.05
    <decltype
    -0.05
    ellas
    -0.05
     ðŁ
    -0.05
     Sof
    -0.05
    ï¸ı
    -0.05
    POSITIVE LOGITS
     overweight
    0.12
     fitness
    0.12
     obesity
    0.11
     FITNESS
    0.11
     Fitness
    0.11
    Fitness
    0.11
     Obesity
    0.11
     weight
    0.10
    fitness
    0.10
     Weight
    0.10
    Activations Density 0.003%

    No Known Activations