© 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. 18261
    Prev
    Next
    INDEX
    Explanations

    instances of the word "on" and related terms or phrases indicating a presence or occurrence

    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
     Humb
    -0.07
    ossip
    -0.06
    Calibri
    -0.06
    ante
    -0.06
    IGH
    -0.06
    egade
    -0.06
    zw
    -0.06
    rid
    -0.05
    SharedPreferences
    -0.05
    âķIJâķIJ
    -0.05
    POSITIVE LOGITS
    ë¿IJ
    0.07
    ersiz
    0.07
    byn
    0.07
    æĮ¯ãĤĬ
    0.07
     ----------------------------------------------------------------------------------------------------------------
    0.07
    errer
    0.07
    uler
    0.07
    uset
    0.07
    xe
    0.07
    razier
    0.07
    Activations Density 0.000%

    No Known Activations