© 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. 118248
    Prev
    Next
    INDEX
    Explanations

    the name "Dob."

    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
    y
    -0.07
    omik
    -0.07
     Straw
    -0.07
    اÛĮØ´
    -0.07
    anou
    -0.07
    erie
    -0.06
    orks
    -0.06
    vig
    -0.06
    enso
    -0.06
     Krish
    -0.06
    POSITIVE LOGITS
     Lam
    0.07
     Karn
    0.06
    annes
    0.06
    .gnu
    0.06
    xfd
    0.06
    etter
    0.06
    ple
    0.06
     Snape
    0.06
    utom
    0.06
    riangle
    0.06
    Activations Density 0.005%

    No Known Activations