© 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. 674
    Prev
    Next
    INDEX
    Explanations

    syntactical elements and the creation of HTML or XML elements in code

    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
    irie
    -0.07
    inant
    -0.07
    isin
    -0.07
    ottes
    -0.07
    kou
    -0.07
    wang
    -0.07
    êu
    -0.07
     Kou
    -0.07
    ntag
    -0.06
    wend
    -0.06
    POSITIVE LOGITS
     span
    0.07
    ISCO
    0.07
     Span
    0.06
     Trafford
    0.06
     stdClass
    0.06
    Span
    0.06
    adesh
    0.06
    cover
    0.06
    aven
    0.06
    -corner
    0.06
    Activations Density 0.003%

    No Known Activations