© 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. 79352
    Prev
    Next
    INDEX
    Explanations

    references to prominent literary or philosophical figures and their works

    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
    ormap
    -0.07
    aunch
    -0.06
    egot
    -0.06
     Passage
    -0.06
    omm
    -0.06
    loh
    -0.06
    ALA
    -0.06
    ionale
    -0.06
    sez
    -0.06
    ipment
    -0.06
    POSITIVE LOGITS
    eko
    0.06
    ertz
    0.06
     Massachusetts
    0.06
    ë
    0.06
     Core
    0.06
     Countdown
    0.06
     Humb
    0.06
    .syntax
    0.06
    );$
    0.06
    æį
    0.06
    Activations Density 0.001%

    No Known Activations