© 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. 73339
    Prev
    Next
    INDEX
    Explanations

    critical issues impacting global development and social justice

    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
    оди
    -0.08
    ä»ĭ
    -0.07
    laughter
    -0.07
    è¥
    -0.07
    erp
    -0.07
    irs
    -0.07
    .problem
    -0.07
    ãĥ¼ãĥī
    -0.07
    ier
    -0.07
    gether
    -0.07
    POSITIVE LOGITS
    ISON
    0.07
     Progress
    0.07
    echan
    0.06
    ADDE
    0.06
    ONTAL
    0.06
     SND
    0.06
     Fey
    0.06
    uze
    0.06
    cob
    0.06
    eware
    0.06
    Activations Density 0.007%

    No Known Activations