© 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. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 62848
    Prev
    Next
    INDEX
    Explanations

    preference and choice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dislikes
    -0.12
     disliked
    -0.10
     preceding
    -0.09
     ideally
    -0.09
     intending
    -0.09
     refusing
    -0.08
     cud
    -0.08
     base
    -0.08
     dislike
    -0.08
     صاد
    -0.08
    POSITIVE LOGITS
     prefer
    0.64
     preference
    0.62
     пÑĢедпоÑĩ
    0.56
     preferred
    0.50
     Preference
    0.47
     prefers
    0.47
     preferences
    0.44
     pref
    0.43
     tercih
    0.43
    prefer
    0.42
    Activations Density 0.288%

    No Known Activations