© 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. 26974
    Prev
    Next
    INDEX
    Explanations

    phrases involving code syntax or function definitions

    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
    _ABI
    -0.07
    (compact
    -0.07
    imeo
    -0.07
     kê
    -0.07
    ABCDEFG
    -0.07
    _cookies
    -0.07
    abela
    -0.07
    StackNavigator
    -0.07
    /raw
    -0.07
     NÄĽm
    -0.07
    POSITIVE LOGITS
     new
    0.12
     replacement
    0.09
     ìĥĪë¡ľìļ´
    0.09
     changed
    0.09
    æĸ°çļĦ
    0.08
     newValue
    0.08
     æĸ°
    0.08
     neue
    0.08
     replacements
    0.08
    (new
    0.07
    Activations Density 0.028%

    No Known Activations