© 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. 124166
    Prev
    Next
    INDEX
    Explanations

    SQL-related expressions and commands

    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
    reu
    -0.07
    æĭ³
    -0.06
    alion
    -0.06
    orio
    -0.06
    ansson
    -0.06
     Bender
    -0.06
    arti
    -0.06
    λιά
    -0.06
    åĨĬ
    -0.06
    hone
    -0.06
    POSITIVE LOGITS
     from
    0.09
     FROM
    0.08
    from
    0.07
    à¸Īาà¸ģ
    0.07
    	FROM
    0.06
     från
    0.06
    dea
    0.06
    stuff
    0.06
     Mus
    0.06
    FromFile
    0.06
    Activations Density 0.004%

    No Known Activations