© 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 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. 17-LLAMASCOPE-RES-131K
    11. 82867
    Prev
    Next
    INDEX
    Explanations

    programming terms and class references in code

    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
    immel
    -0.06
     éħ
    -0.06
    ekil
    -0.06
    áž
    -0.06
    हल
    -0.06
     GetMessage
    -0.06
     (
    -0.05
     Caj
    -0.05
    spl
    -0.05
    моÑĤ
    -0.05
    POSITIVE LOGITS
    AccessType
    0.08
    TypeEnum
    0.08
    Constants
    0.08
    opis
    0.08
    indsight
    0.07
    avou
    0.07
    aepernick
    0.07
    oralType
    0.07
     McCabe
    0.07
     FileMode
    0.07
    Activations Density 0.050%

    No Known Activations