© 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. 123831
    Prev
    Next
    INDEX
    Explanations

    numerical data related to years and statistics

    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
    ä¼ı
    -0.09
    acic
    -0.08
    ptom
    -0.07
    robat
    -0.07
    ierz
    -0.07
    walker
    -0.07
    ubre
    -0.07
    stanov
    -0.07
    ablish
    -0.07
    etik
    -0.07
    POSITIVE LOGITS
    onde
    0.06
     createSelector
    0.06
    alc
    0.06
    undi
    0.05
    cast
    0.05
     ÙħÛĮÙĦادÛĮ
    0.05
    bye
    0.05
    umi
    0.05
     åIJ
    0.05
    idal
    0.05
    Activations Density 0.001%

    No Known Activations