© 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. 71449
    Prev
    Next
    INDEX
    Explanations

    programming language syntax and related constructs

    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
    yl
    -0.07
    ully
    -0.06
     chains
    -0.06
    etch
    -0.06
     Et
    -0.06
    uzz
    -0.06
    834
    -0.06
     Gunn
    -0.06
     Cohen
    -0.06
    ged
    -0.06
    POSITIVE LOGITS
    ','','
    0.07
    ","","
    0.07
    disposed
    0.07
    opy
    0.06
    alfa
    0.06
     vòng
    0.06
    iset
    0.06
    hap
    0.06
    :list
    0.06
    CRET
    0.06
    Activations Density 0.013%

    No Known Activations