© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 5-LLAMASCOPE-RES-131K
    11. 125601
    Prev
    Next
    INDEX
    Explanations

    programming-related function calls and debugging terms

    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
     Patel
    -0.06
    zes
    -0.06
    kl
    -0.06
    jev
    -0.06
    izza
    -0.06
    ttp
    -0.06
    izio
    -0.06
    ermal
    -0.06
     mean
    -0.06
    118
    -0.06
    POSITIVE LOGITS
    isclosed
    0.08
    aths
    0.08
    GPC
    0.07
    acom
    0.07
     trav
    0.07
    ãĥªãĥ¼ãĤº
    0.07
    pcm
    0.07
    arty
    0.07
    иÑĤив
    0.07
    reur
    0.07
    Activations Density 0.001%

    No Known Activations