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. 22-LLAMASCOPE-RES-131K
    6. 5314
    Prev
    Next
    INDEX
    Explanations

    occurrences of the variable 'a' in coding or programming contexts

    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
     special
    -0.08
    ç®Ĭ
    -0.07
    Special
    -0.07
    special
    -0.07
     Special
    -0.07
    .asInstanceOf
    -0.06
    çī¹åĪ¥
    -0.06
     calling
    -0.06
    ungan
    -0.06
    ģ
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.10
    aken
    0.07
    DataURL
    0.07
    Lens
    0.07
    elman
    0.07
    ighted
    0.07
    ÅĻÃŃž
    0.07
     mon
    0.07
    ats
    0.07
    .syntax
    0.07
    Activations Density 0.000%

    No Known Activations