© 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. 35506
    Prev
    Next
    INDEX
    Explanations

    name of [entity]

    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
     Umb
    -0.10
     naming
    -0.09
     marked
    -0.09
     Samp
    -0.09
     Factory
    -0.08
     grouped
    -0.08
     Marshall
    -0.08
     Went
    -0.08
     Bian
    -0.08
     Go
    -0.08
    POSITIVE LOGITS
     eg
    0.09
    inclu
    0.09
    :".$
    0.09
    ikk
    0.09
     followed
    0.09
    resp
    0.09
     плÑİ
    0.09
    ahi
    0.09
    =__
    0.08
    ophy
    0.08
    Activations Density 0.111%

    No Known Activations