© 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. 15-LLAMASCOPE-RES-131K
    11. 87063
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods and their usage in defining sentence structure

    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
    abi
    -0.07
    ecut
    -0.07
    imple
    -0.07
     plá
    -0.07
    enso
    -0.07
    anki
    -0.07
    iá»ĥn
    -0.07
    egr
    -0.07
    coni
    -0.07
    DBG
    -0.06
    POSITIVE LOGITS
     Secondly
    0.07
     Milo
    0.06
    iges
    0.06
    FFE
    0.06
    de
    0.06
    ickets
    0.06
    elay
    0.05
     notwithstanding
    0.05
    To
    0.05
    )null
    0.05
    Activations Density 0.004%

    No Known Activations