© 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. 103669
    Prev
    Next
    INDEX
    Explanations

    programming-related function and method calls

    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
     ÑģпÑĢави
    -0.07
    ambre
    -0.07
    uary
    -0.07
    обÑĢаÐ
    -0.07
    istr
    -0.07
    TickCount
    -0.07
    tober
    -0.07
    flix
    -0.07
    ilee
    -0.07
     isKindOfClass
    -0.07
    POSITIVE LOGITS
    rame
    0.06
    .gif
    0.06
    ¿
    0.06
    661
    0.06
     Watt
    0.05
    (
    0.05
    ();
    0.05
    .nih
    0.05
    alla
    0.05
    AMED
    0.05
    Activations Density 0.028%

    No Known Activations