© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 58067
    Prev
    Next
    INDEX
    Explanations

    elements related to artistic techniques and expressions

    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
     Seal
    -0.06
    SSERT
    -0.06
    æ¼Ķ
    -0.06
    pluck
    -0.06
    lore
    -0.06
     Team
    -0.06
    è°±
    -0.06
    urve
    -0.06
     Films
    -0.06
    äºŃ
    -0.06
    POSITIVE LOGITS
     artist
    0.10
     artists
    0.09
     Fine
    0.09
    -gallery
    0.09
    artist
    0.08
     studio
    0.08
     gallery
    0.08
     Artists
    0.08
     art
    0.08
    artists
    0.08
    Activations Density 1.149%

    No Known Activations