© 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. 95097
    Prev
    Next
    INDEX
    Explanations

    references to academic conferences and seminars

    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
    anda
    -0.07
     lif
    -0.06
    owie
    -0.06
    Studio
    -0.06
    asser
    -0.05
     na
    -0.05
    対
    -0.05
     left
    -0.05
     заг
    -0.05
    ¶Į
    -0.05
    POSITIVE LOGITS
     held
    0.09
    held
    0.09
     Held
    0.08
    -held
    0.08
    INGER
    0.07
    ,},↵
    0.07
     %[
    0.07
    ëĬIJ
    0.07
    .sponge
    0.07
    ncpy
    0.07
    Activations Density 0.025%

    No Known Activations