© 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. 84462
    Prev
    Next
    INDEX
    Explanations

    actions related to the creation or implementation of components 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
    '])?
    -0.08
    unc
    -0.07
    %X
    -0.07
    passport
    -0.06
    Amb
    -0.06
    amb
    -0.06
    ne
    -0.06
    ula
    -0.06
    aty
    -0.06
    aten
    -0.06
    POSITIVE LOGITS
    oucher
    0.07
    æĸ°çļĦ
    0.07
     new
    0.07
    OrUpdate
    0.07
     separate
    0.07
    iem
    0.07
     empty
    0.06
    krom
    0.06
    isu
    0.06
    olet
    0.06
    Activations Density 0.018%

    No Known Activations