© 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. 5394
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Jason."

    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
    uter
    -0.10
    ongyang
    -0.08
    entes
    -0.08
    klad
    -0.08
    ubern
    -0.07
    ToBounds
    -0.07
    ÄĻd
    -0.07
    лоÑĩ
    -0.07
    ORB
    -0.07
    RowAt
    -0.07
    POSITIVE LOGITS
    emic
    0.06
     div
    0.06
    nd
    0.06
    n
    0.06
    oggler
    0.06
    lek
    0.06
     flu
    0.06
     compl
    0.06
    ariant
    0.05
     æ¹
    0.05
    Activations Density 0.012%

    No Known Activations