© 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. 125999
    Prev
    Next
    INDEX
    Explanations

    references to coding styles and structures in programming-related text

    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
     mam
    -0.06
    uta
    -0.06
     ActionTypes
    -0.06
    urg
    -0.06
    GG
    -0.05
    .tc
    -0.05
     *__
    -0.05
     incon
    -0.05
     sama
    -0.05
    ourg
    -0.05
    POSITIVE LOGITS
     addCriterion
    0.08
    rier
    0.07
    others
    0.07
    485
    0.07
    lisi
    0.07
    ustos
    0.07
    iasco
    0.07
    .Emit
    0.07
    IColor
    0.06
    ä¾
    0.06
    Activations Density 0.008%

    No Known Activations