© 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. 15-LLAMASCOPE-RES-131K
    11. 86669
    Prev
    Next
    INDEX
    Explanations

    instances of the word "gone" and its variations, indicating loss or absence

    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
    son
    -0.07
    tual
    -0.06
    ors
    -0.06
    loses
    -0.06
    ovsky
    -0.06
    orsch
    -0.06
    αÏģ
    -0.06
    rror
    -0.06
    los
    -0.06
    loi
    -0.06
    POSITIVE LOGITS
    adic
    0.08
    ned
    0.07
    LOPT
    0.07
    ή
    0.06
    amate
    0.06
    ader
    0.06
    ption
    0.06
    317
    0.06
    erg
    0.06
    lal
    0.06
    Activations Density 0.015%

    No Known Activations