© 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. 29172
    Prev
    Next
    INDEX
    Explanations

    numerical identifiers related to books, specifically ISBN numbers

    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
    uw
    -0.07
    abo
    -0.06
    oped
    -0.06
    æݨ
    -0.06
    onde
    -0.06
    uart
    -0.06
     Ladies
    -0.06
    inspace
    -0.06
    andra
    -0.05
     Liter
    -0.05
    POSITIVE LOGITS
    @qq
    0.07
    geh
    0.07
    ningen
    0.07
    /stdc
    0.07
    entic
    0.07
    entes
    0.07
    elden
    0.07
    ï¼Ń
    0.06
    ernels
    0.06
    ERP
    0.06
    Activations Density 0.005%

    No Known Activations