© 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. 117428
    Prev
    Next
    INDEX
    Explanations

    various punctuation marks and formatting elements

    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
    ottle
    -0.07
    alborg
    -0.07
    usp
    -0.07
    UCKET
    -0.07
    ERCHANT
    -0.06
    oton
    -0.06
    hetto
    -0.06
    Middleware
    -0.06
    foundland
    -0.06
    itunes
    -0.06
    POSITIVE LOGITS
    zig
    0.07
     newsletters
    0.06
     background
    0.06
    odel
    0.06
     vlas
    0.06
    DW
    0.06
    oui
    0.06
    æļ
    0.06
     opaque
    0.06
    raz
    0.06
    Activations Density 0.001%

    No Known Activations