© 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 EvalsExportsAPI 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. 57283
    Prev
    Next
    INDEX
    Explanations

    descriptions and characteristics of various artistic and cultural elements

    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
    semblies
    -0.06
    ÙĦب
    -0.06
    znik
    -0.06
    inu
    -0.06
     union
    -0.06
    sembly
    -0.06
    ekk
    -0.06
     bilateral
    -0.06
     Formatting
    -0.05
     Winning
    -0.05
    POSITIVE LOGITS
     each
    0.20
    each
    0.19
     Each
    0.17
     EACH
    0.17
    Each
    0.17
    .each
    0.15
    (each
    0.14
    åIJĦ
    0.13
     кажд
    0.13
     different
    0.13
    Activations Density 0.096%

    No Known Activations