© 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. 108315
    Prev
    Next
    INDEX
    Explanations

    the word "of" in various contexts

    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
    ãĥ
    -0.07
    باØŃ
    -0.07
     topl
    -0.07
    ÑĨеп
    -0.07
     -*
    -0.06
    iem
    -0.06
    باش
    -0.06
    .attachment
    -0.06
     ****************
    -0.06
    ãĥĩãĤ£ãĤ¢
    -0.06
    POSITIVE LOGITS
    anner
    0.08
    azzi
    0.08
    itä
    0.08
    abox
    0.07
    regnum
    0.07
    duit
    0.07
    arend
    0.07
    ButtonTitles
    0.07
    ös
    0.07
    itest
    0.07
    Activations Density 0.181%

    No Known Activations