© 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. 17-LLAMASCOPE-RES-131K
    11. 40145
    Prev
    Next
    INDEX
    Explanations

    coding elements and function definitions in a programming context

    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
    avirus
    -0.07
    omal
    -0.06
    ongyang
    -0.06
    izon
    -0.06
    oleon
    -0.06
    ÄĽl
    -0.06
    ummings
    -0.06
    rys
    -0.06
     bergen
    -0.05
     Bris
    -0.05
    POSITIVE LOGITS
    ãĥ³ãĤ¹
    0.07
    utin
    0.06
    haar
    0.06
    andi
    0.06
     Twin
    0.06
     ï¿¥
    0.06
     Ú¯ÛĮ
    0.06
    ÑĤоÑĩ
    0.06
     Primitive
    0.06
     ...(
    0.06
    Activations Density 0.021%

    No Known Activations