© 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. 4596
    Prev
    Next
    INDEX
    Explanations

    references to fine arts education and qualifications

    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
    urd
    -0.06
     phụ
    -0.06
    Brains
    -0.06
     Sud
    -0.06
    Invoker
    -0.06
     STEM
    -0.06
    гл
    -0.06
    abyrin
    -0.06
    oren
    -0.05
    unda
    -0.05
    POSITIVE LOGITS
     studio
    0.10
     studios
    0.10
     Studio
    0.09
    studio
    0.08
     Studios
    0.08
    Studio
    0.08
     Artist
    0.07
     artist
    0.07
     Creative
    0.07
    cheon
    0.07
    Activations Density 0.044%

    No Known Activations