© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 94592
    Prev
    Next
    INDEX
    Explanations

    instances of strong emotion or significant tension

    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
    ovice
    -0.07
    udder
    -0.07
    abal
    -0.07
    ertest
    -0.07
    riv
    -0.07
    existent
    -0.06
    idor
    -0.06
     mechan
    -0.06
    -0.06
    éĿ©åij½
    -0.06
    POSITIVE LOGITS
     upto
    0.07
    istik
    0.06
     Citizenship
    0.06
     atleast
    0.06
     Irvine
    0.06
     imkân
    0.06
     Hence
    0.06
    bakan
    0.06
     hence
    0.06
    umont
    0.06
    Activations Density 0.000%

    No Known Activations