© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 90387
    Prev
    Next
    INDEX
    Explanations

    programming context and execution control structures

    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
    OPS
    -0.07
    abra
    -0.07
    ymi
    -0.07
    ardon
    -0.06
     Unidos
    -0.06
    ops
    -0.06
    é
    -0.06
     tiener
    -0.06
    vendor
    -0.06
    icha
    -0.06
    POSITIVE LOGITS
    .HttpContext
    0.07
    uger
    0.07
    Variables
    0.07
     Variables
    0.06
    iley
    0.06
    conditions
    0.06
     Threads
    0.06
    REFERRED
    0.06
     EventArgs
    0.06
    Vars
    0.06
    Activations Density 0.052%

    No Known Activations