© 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. 41870
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "or."

    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
    egan
    -0.07
    /or
    -0.06
    Äĥn
    -0.06
    gency
    -0.06
    enor
    -0.06
    allas
    -0.06
    swer
    -0.06
    pler
    -0.06
    utsche
    -0.06
    ecessarily
    -0.06
    POSITIVE LOGITS
    ù
    0.07
    iani
    0.06
    iol
    0.06
    uin
    0.06
    ignal
    0.06
    æĽ´å¤ļ
    0.06
    /var
    0.06
    cmath
    0.06
    _capabilities
    0.06
     Mohamed
    0.06
    Activations Density 0.012%

    No Known Activations