© 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 EvalsExportsAPI 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. 93875
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and numbers

    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
     fur
    -0.06
    nis
    -0.06
    porter
    -0.06
    oster
    -0.06
    oler
    -0.06
    eni
    -0.06
    nun
    -0.06
    ergy
    -0.06
     Redistribution
    -0.06
    jon
    -0.06
    POSITIVE LOGITS
     LENG
    0.07
    edor
    0.07
    تÙī
    0.07
     Ø¢Ùħار
    0.07
    antal
    0.07
    (æ°´
    0.07
     ----------------------------------------------------------------------↵
    0.07
     Trafford
    0.06
    جÙĨ
    0.06
    UniqueId
    0.06
    Activations Density 0.031%

    No Known Activations