© 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 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. 29189
    Prev
    Next
    INDEX
    Explanations

    elements related to mystery and hidden narratives

    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
     addCriterion
    -0.07
    theid
    -0.07
    iasm
    -0.07
    .IContainer
    -0.07
    ughter
    -0.06
    enen
    -0.06
    ibu
    -0.06
    avis
    -0.06
    eties
    -0.06
    etration
    -0.06
    POSITIVE LOGITS
    pch
    0.07
    ă
    0.07
     your
    0.07
    æĤ¨çļĦ
    0.07
    ì¹
    0.06
     escapes
    0.06
    uyá»ģn
    0.06
    ç¹ģ
    0.06
    ãĤ¯ãĥŃ
    0.06
    erah
    0.06
    Activations Density 0.001%

    No Known Activations