© 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. 94725
    Prev
    Next
    INDEX
    Explanations

    references to the history of art, particularly Western art and related scholarly resources

    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
    imus
    -0.08
    utters
    -0.08
    еÑĢжав
    -0.07
     воÑĢ
    -0.07
     thiá»ĩn
    -0.07
    swick
    -0.07
    coil
    -0.07
    inflate
    -0.07
     historical
    -0.07
     paci
    -0.07
    POSITIVE LOGITS
     ideas
    0.07
     Ideas
    0.06
     Dre
    0.06
     Ging
    0.06
     fileprivate
    0.06
    izzy
    0.06
     Rooney
    0.06
    ideas
    0.05
    bro
    0.05
    _decl
    0.05
    Activations Density 0.013%

    No Known Activations