© 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. 62272
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific visual or poetic imagery, particularly related to colors and floral motifs

    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
    eland
    -0.07
    ebek
    -0.07
    imulator
    -0.07
    otherapy
    -0.07
     zah
    -0.07
    argon
    -0.07
    á»ħ
    -0.07
    oftware
    -0.07
     ----------------------------------------------------------------------↵
    -0.07
    еÑĢап
    -0.06
    POSITIVE LOGITS
    gers
    0.08
    /stdc
    0.06
    arian
    0.06
    tran
    0.06
    :CGRect
    0.06
    اÙĦÙĬا
    0.05
    dech
    0.05
    anced
    0.05
    anim
    0.05
    richt
    0.05
    Activations Density 0.001%

    No Known Activations