© 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. 108266
    Prev
    Next
    INDEX
    Explanations

    technical terms and code-related functionalities

    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
    ÑĦика
    -0.07
    ricks
    -0.07
    reamble
    -0.07
    kenin
    -0.06
    ceipt
    -0.06
    enzyme
    -0.06
    ;element
    -0.06
    /Peak
    -0.06
    .Logf
    -0.06
     Merkez
    -0.06
    POSITIVE LOGITS
     rules
    0.07
    ruh
    0.06
    rules
    0.06
    리ìĸ´
    0.06
    eten
    0.06
     catch
    0.06
     Deposit
    0.06
    .rules
    0.06
    umu
    0.06
     Elev
    0.06
    Activations Density 0.001%

    No Known Activations