© 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. 73268
    Prev
    Next
    INDEX
    Explanations

    elements related to artistic expression and visual arts

    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
    voj
    -0.07
     أص
    -0.07
    мага
    -0.07
    porte
    -0.07
    itar
    -0.07
    anz
    -0.07
    ampo
    -0.07
    015
    -0.07
    illon
    -0.07
    erra
    -0.06
    POSITIVE LOGITS
    lav
    0.06
    -svg
    0.06
    Viewer
    0.06
     baz
    0.06
     Viewer
    0.06
     Baz
    0.06
    æ±Ĥ
    0.06
    orgia
    0.06
    ills
    0.06
    pons
    0.06
    Activations Density 0.016%

    No Known Activations