© 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. 27929
    Prev
    Next
    INDEX
    Explanations

    references to listings or citations in the text

    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
    enge
    -0.07
    ean
    -0.07
    otron
    -0.06
    tridge
    -0.06
    ouri
    -0.06
    åī¯
    -0.06
    еди
    -0.06
    .getElementsByName
    -0.06
    eking
    -0.06
    icious
    -0.05
    POSITIVE LOGITS
    ìļ¸
    0.07
     arrow
    0.07
     Ùħرتب
    0.07
    _Insert
    0.07
    Gratis
    0.07
    KIT
    0.07
    à¹Īละ
    0.07
    arrow
    0.07
     arrows
    0.07
    纯
    0.06
    Activations Density 0.006%

    No Known Activations