© 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. 106927
    Prev
    Next
    INDEX
    Explanations

    code-related syntax and structure, particularly in programming languages

    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
    gear
    -0.07
    icipant
    -0.07
    HING
    -0.06
    ÙĬدا
    -0.06
    imately
    -0.06
    _relu
    -0.06
    attro
    -0.06
    asc
    -0.06
    agg
    -0.06
    avras
    -0.06
    POSITIVE LOGITS
    okol
    0.07
    lsa
    0.07
    iset
    0.07
    biased
    0.07
    ãĥ¼ãĥ«ãĥī
    0.06
    .FC
    0.06
    OnInit
    0.06
    ÃĸL
    0.06
     unbiased
    0.06
    еÑĢаÑĤоÑĢ
    0.06
    Activations Density 0.001%

    No Known Activations