© 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. 54800
    Prev
    Next
    INDEX
    Explanations

    programming-related terminology

    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
    Arg
    -0.06
    _bindings
    -0.06
     Arg
    -0.06
    rodu
    -0.06
    activex
    -0.05
    /environment
    -0.05
    rawn
    -0.05
    arg
    -0.05
     programmes
    -0.05
    Argument
    -0.05
    POSITIVE LOGITS
     fields
    0.10
     field
    0.09
     Fields
    0.08
    fields
    0.08
    åŃĹ段
    0.07
     foreign
    0.07
     полÑı
    0.07
    nullable
    0.07
     relationship
    0.07
    abwe
    0.07
    Activations Density 0.110%

    No Known Activations