© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 43714
    Prev
    Next
    INDEX
    Explanations

    ingredient line

    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
    cep
    -0.10
    Mounted
    -0.10
     terr
    -0.09
     RESERVED
    -0.09
    Ｉ
    -0.09
    loub
    -0.09
     acidic
    -0.09
     Falk
    -0.09
     Wyn
    -0.09
     Cecil
    -0.09
    POSITIVE LOGITS
     pres
    0.16
    Contains
    0.14
     ingredients
    0.14
     artificial
    0.13
     DRV
    0.13
     Contains
    0.13
     ingredient
    0.12
     shelf
    0.12
     allerg
    0.12
     contains
    0.12
    Activations Density 0.043%

    No Known Activations