© 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. 31215
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly commas 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
    mor
    -0.07
    lut
    -0.06
    :,
    -0.06
    imir
    -0.06
    ,
    -0.06
    ##_
    -0.06
    ptal
    -0.06
     then
    -0.06
     tro
    -0.06
    enza
    -0.06
    POSITIVE LOGITS
     Trab
    0.08
    (od
    0.07
    dera
    0.07
     بتÙĨ
    0.07
    ould
    0.07
    æ¦
    0.07
    اتÙĩ
    0.06
    جÙĩ
    0.06
    etin
    0.06
    abinet
    0.06
    Activations Density 0.015%

    No Known Activations