© 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. 74081
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to class and service definitions

    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
    rif
    -0.07
    quisites
    -0.07
    processable
    -0.07
    razier
    -0.06
    fol
    -0.06
    heim
    -0.06
    ç±
    -0.06
    upp
    -0.06
     Möglichkeit
    -0.06
    bia
    -0.06
    POSITIVE LOGITS
     gre
    0.07
    YNC
    0.06
    اشت
    0.06
     sat
    0.06
     =>$
    0.06
     xá»Ń
    0.06
    ritel
    0.06
     mê
    0.06
    kus
    0.06
    ync
    0.06
    Activations Density 0.008%

    No Known Activations