© 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. 30584
    Prev
    Next
    INDEX
    Explanations

    concepts related to voting, acoustic signals, and consumer products

    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
     remainder
    -0.10
     rest
    -0.07
    ennen
    -0.07
    afa
    -0.07
    Ross
    -0.07
    hausen
    -0.06
     Stap
    -0.06
    ór
    -0.06
    нки
    -0.06
    bilder
    -0.06
    POSITIVE LOGITS
     most
    0.14
     least
    0.12
     ê°Ģìŀ¥
    0.12
    least
    0.12
     MOST
    0.11
    most
    0.11
     fur
    0.10
    -most
    0.10
    _most
    0.09
     सबस
    0.09
    Activations Density 0.033%

    No Known Activations