© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 39157
    Prev
    Next
    INDEX
    Explanations

    fields and attributes

    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
    INFRINGEMENT
    -0.10
    <|begin_of_text|>
    -0.09
    füg
    -0.09
    SSI
    -0.09
    ntax
    -0.09
    byname
    -0.09
    uide
    -0.09
    ¯¯
    -0.09
    EMPLARY
    -0.09
     STDCALL
    -0.08
    POSITIVE LOGITS
     fields
    0.16
     record
    0.14
     recording
    0.13
     foreign
    0.12
     Fields
    0.12
     recorded
    0.12
    fields
    0.12
     flags
    0.12
    ForeignKey
    0.12
     associated
    0.11
    Activations Density 0.128%

    No Known Activations