© 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
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 38887
    Prev
    Next
    INDEX
    Explanations

    it is a

    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
     undermining
    -0.11
     undermined
    -0.10
     mean
    -0.10
    SSL
    -0.08
    bung
    -0.08
     misdemean
    -0.08
    dsa
    -0.08
     always
    -0.08
    idot
    -0.08
     Brut
    -0.08
    POSITIVE LOGITS
     borders
    0.17
     border
    0.15
     verg
    0.15
     amounts
    0.14
     amount
    0.14
    amount
    0.13
     Amount
    0.12
    tant
    0.12
     sm
    0.12
     Borders
    0.11
    Activations Density 0.160%

    No Known Activations