© 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. 9-LLAMASCOPE-RES-131K
    11. 98419
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically focusing on exclamation points and periods

    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
    roit
    -0.06
    ayload
    -0.06
    worm
    -0.06
    ankind
    -0.06
    ends
    -0.06
     Owens
    -0.06
    ì°¨
    -0.06
    553
    -0.06
     geile
    -0.06
    ystore
    -0.05
    POSITIVE LOGITS
    .eth
    0.09
    çļ®
    0.07
    /stdc
    0.07
    _eth
    0.06
    ubits
    0.06
    blr
    0.06
     Reform
    0.06
    alla
    0.06
    itm
    0.06
    .dw
    0.06
    Activations Density 0.013%

    No Known Activations