© 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. 29163
    Prev
    Next
    INDEX
    Explanations

    references to programming or coding elements related to laboratory processes and version control

    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
    ürn
    -0.06
    olet
    -0.06
     Erotische
    -0.06
    enek
    -0.06
    antz
    -0.06
     vert
    -0.06
    acomment
    -0.05
    oteca
    -0.05
    neath
    -0.05
    rets
    -0.05
    POSITIVE LOGITS
    ìļ©
    0.08
     ActionTypes
    0.07
    ActionPerformed
    0.07
    GREE
    0.07
    ;charset
    0.07
    gnore
    0.07
    (TM
    0.07
    oodles
    0.07
    -SA
    0.07
    ınıf
    0.07
    Activations Density 0.038%

    No Known Activations