© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 27228
    Prev
    Next
    INDEX
    Explanations

    code-related syntax and functions in 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
    uries
    -0.08
    acci
    -0.08
    à¥ĭà¤ļ
    -0.08
    jez
    -0.08
     tetas
    -0.08
    opal
    -0.08
    ogui
    -0.08
    orgia
    -0.08
    rylic
    -0.07
    odos
    -0.07
    POSITIVE LOGITS
    0.07
     IN
    0.06
     Lam
    0.06
     resist
    0.06
     M
    0.05
    poser
    0.05
     Lamb
    0.05
     meg
    0.05
     tab
    0.05
     (
    0.05
    Activations Density 0.019%

    No Known Activations