© 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. 9-LLAMASCOPE-RES-131K
    11. 97824
    Prev
    Next
    INDEX
    Explanations

    phrases indicating personal considerations and opinions

    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
    ÅĽnie
    -0.08
    ekt
    -0.07
    hlen
    -0.07
    error
    -0.06
    balances
    -0.06
    ulan
    -0.06
    çŃĴ
    -0.06
    anki
    -0.06
    esen
    -0.06
    udeau
    -0.06
    POSITIVE LOGITS
     yourself
    0.07
     either
    0.06
    ousel
    0.06
     mild
    0.06
     or
    0.06
     McGr
    0.06
     Dawson
    0.06
    /repository
    0.06
     regular
    0.06
    eward
    0.05
    Activations Density 0.015%

    No Known Activations