© 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. 72719
    Prev
    Next
    INDEX
    Explanations

    numerical data points and their contextual associations, particularly related to time periods 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
    znam
    -0.08
    دارÛĮ
    -0.08
    館
    -0.08
     Danh
    -0.07
    owski
    -0.07
    кап
    -0.07
    abwe
    -0.07
    imd
    -0.07
    ç¹Ķ
    -0.07
     åIJī
    -0.07
    POSITIVE LOGITS
     last
    0.07
    æĬľ
    0.06
     vs
    0.06
     data
    0.06
    last
    0.06
     recently
    0.06
    latest
    0.06
     último
    0.06
     latest
    0.06
    rem
    0.05
    Activations Density 0.015%

    No Known Activations