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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 5080
    Prev
    Next
    INDEX
    Explanations

    phrases related to function calls and parameters within programming contexts

    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
    utsch
    -0.07
    ichel
    -0.06
    uci
    -0.06
    лада
    -0.06
    hab
    -0.06
    urd
    -0.06
    屬
    -0.06
    ucu
    -0.06
    agit
    -0.06
    ums
    -0.06
    POSITIVE LOGITS
     callers
    0.11
     caller
    0.10
     clients
    0.09
    caller
    0.09
     users
    0.09
     calling
    0.08
     Caller
    0.08
     applications
    0.08
     downstream
    0.08
     client
    0.07
    Activations Density 0.068%

    No Known Activations