Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 29367
    Prev
    Next
    INDEX
    Explanations

    syntax elements and structural components in programming 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
    _scheme
    -0.07
    809
    -0.07
    itu
    -0.06
     bour
    -0.06
    .Tick
    -0.06
    pend
    -0.06
    essional
    -0.06
    Sessions
    -0.06
    OrDefault
    -0.06
    eting
    -0.06
    POSITIVE LOGITS
    udas
    0.07
    /Foundation
    0.07
    kami
    0.07
    swagen
    0.06
    ukan
    0.06
    ô
    0.06
    DbType
    0.06
    <html
    0.06
    RootElement
    0.06
    orum
    0.06
    Activations Density 0.004%

    No Known Activations