© 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. 9-LLAMASCOPE-RES-131K
    11. 98178
    Prev
    Next
    INDEX
    Explanations

    references to significant contributions or quality in the arts, particularly regarding film and women filmmakers

    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
    aby
    -0.08
    ahi
    -0.07
    angi
    -0.07
    Columns
    -0.06
    ime
    -0.06
    oyer
    -0.06
    ´Ī
    -0.05
    hazi
    -0.05
    aney
    -0.05
     unravel
    -0.05
    POSITIVE LOGITS
    soap
    0.08
    озд
    0.07
    jos
    0.06
     à¤ļà¤ķ
    0.06
    иÑĤи
    0.06
    Ø·Ùħ
    0.06
    æĻ´
    0.06
    íļ¨
    0.06
     Choices
    0.06
     Jog
    0.06
    Activations Density 0.005%

    No Known Activations