© 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. 15017
    Prev
    Next
    INDEX
    Explanations

    punctuations and speech markers indicating various tones or shifts in conversation

    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
    lev
    -0.07
    ober
    -0.07
    ily
    -0.06
    ï
    -0.06
    Refer
    -0.06
    refer
    -0.06
     ï
    -0.06
     alike
    -0.06
     re
    -0.06
    uth
    -0.06
    POSITIVE LOGITS
     /*č↵
    0.09
    YPRE
    0.08
    iode
    0.07
    _lifetime
    0.07
    $LANG
    0.07
    ascript
    0.07
    adaÅŁ
    0.07
    iá»ģm
    0.07
    üven
    0.07
    iá»ĥu
    0.07
    Activations Density 0.036%

    No Known Activations