© 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. 82014
    Prev
    Next
    INDEX
    Explanations

    references to labor and work-related concepts

    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
    ema
    -0.07
    eof
    -0.07
    enger
    -0.07
    ãĥ³ãĥĸ
    -0.07
    sis
    -0.07
    pling
    -0.07
    ennie
    -0.07
    UTO
    -0.06
    cheng
    -0.06
    Å¡ti
    -0.06
    POSITIVE LOGITS
    ious
    0.11
    iously
    0.11
    atorium
    0.09
    iginal
    0.09
    bers
    0.09
     force
    0.08
    aru
    0.08
    ers
    0.08
    IOUS
    0.08
    ites
    0.07
    Activations Density 0.008%

    No Known Activations