© 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. 58450
    Prev
    Next
    INDEX
    Explanations

    instances of the word "less."

    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
    .asm
    -0.07
    egas
    -0.06
    irc
    -0.06
    .nih
    -0.06
    aģın
    -0.06
    ñana
    -0.06
     Ùħت
    -0.06
    ua
    -0.06
    pert
    -0.05
    errupted
    -0.05
    POSITIVE LOGITS
    kola
    0.07
    zdy
    0.07
    etim
    0.06
    atee
    0.06
    enza
    0.06
    xcb
    0.06
    chet
    0.06
     TValue
    0.06
    Äįe
    0.06
    ets
    0.06
    Activations Density 0.000%

    No Known Activations