© 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. 97390
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation or formatting indicators

    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
    á»ijng
    -0.07
     slou
    -0.07
    èĨľ
    -0.07
    mma
    -0.07
    ilim
    -0.06
    à¸ķร
    -0.06
     Garr
    -0.06
    rogate
    -0.06
    teg
    -0.06
    vale
    -0.06
    POSITIVE LOGITS
    .SimpleButton
    0.07
    957
    0.07
     containing
    0.06
    ÏĨÎŃ
    0.06
    ãĥªãĥ¼ãĤº
    0.05
    .Toolkit
    0.05
     Kut
    0.05
    .Schema
    0.05
    çľł
    0.05
    Æ°á»Ŀng
    0.05
    Activations Density 0.001%

    No Known Activations