© 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. 117814
    Prev
    Next
    INDEX
    Explanations

    phrases expressing inadequacy or insufficient effort

    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
    ανά
    -0.07
    uspend
    -0.07
    alette
    -0.06
    .qq
    -0.06
    Trader
    -0.06
    åłĤ
    -0.06
    ourmet
    -0.06
    iq
    -0.06
    zano
    -0.06
    ruž
    -0.06
    POSITIVE LOGITS
     too
    0.18
    too
    0.17
     Too
    0.17
    Too
    0.17
     TOO
    0.17
    太
    0.14
    -too
    0.14
     ÑģлиÑĪком
    0.14
    _TOO
    0.13
     太
    0.12
    Activations Density 0.117%

    No Known Activations