© 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. 124705
    Prev
    Next
    INDEX
    Explanations

    the word "couple" indicating instances of pairs or groups

    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
    resses
    -0.08
    jom
    -0.07
    ayers
    -0.07
    ORIES
    -0.07
    ayer
    -0.06
    arth
    -0.06
    esel
    -0.06
    ron
    -0.06
    én
    -0.06
    188
    -0.06
    POSITIVE LOGITS
     of
    0.16
     dozen
    0.14
    OfFile
    0.09
    à¸Ĥà¸Ńà¸ĩà¸ľ
    0.09
     của
    0.09
     hundred
    0.08
    _of
    0.08
    OfString
    0.08
    of
    0.08
    e
    0.08
    Activations Density 0.006%

    No Known Activations