© 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. 92479
    Prev
    Next
    INDEX
    Explanations

    occurrences of parentheses and their significance in the text context

    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
    -0.07
    110
    -0.06
     vs
    -0.06
    èĤ©
    -0.06
    1
    -0.06
     audition
    -0.06
    pg
    -0.06
    aid
    -0.06
    ghi
    -0.06
     nav
    -0.05
    POSITIVE LOGITS
    #ab
    0.09
    @brief
    0.08
     Bylo
    0.08
    istrovstvÃŃ
    0.08
    /latest
    0.08
    Serialized
    0.07
    .Raise
    0.07
    _OP
    0.07
    DisplayStyle
    0.07
    #ad
    0.07
    Activations Density 0.001%

    No Known Activations