© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 50125
    Prev
    Next
    INDEX
    Explanations

    come with

    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
    ammo
    -0.10
     acquaint
    -0.10
    amam
    -0.09
    ldr
    -0.09
    ondo
    -0.08
    ï½°
    -0.08
    oogle
    -0.08
    é³
    -0.08
    дон
    -0.08
    licable
    -0.08
    POSITIVE LOGITS
     accompanying
    0.49
     accompany
    0.47
     associated
    0.46
    ä¼´
    0.45
     accompanies
    0.43
    associated
    0.36
     kèm
    0.35
     ÑģопÑĢов
    0.34
     ÙĩÙħراÙĩ
    0.33
     accompagn
    0.32
    Activations Density 0.178%

    No Known Activations