© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 58040
    Prev
    Next
    INDEX
    Explanations

    turn followed by red, into, or heads

    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
    ual
    -0.11
    UAL
    -0.09
    ught
    -0.09
    594
    -0.09
    olate
    -0.09
    501
    -0.08
     Troy
    -0.08
    _align
    -0.08
     conscience
    -0.08
    strup
    -0.08
    POSITIVE LOGITS
    tables
    0.20
     tables
    0.15
     heads
    0.14
    ips
    0.14
     tide
    0.14
     Tables
    0.14
    stile
    0.13
    table
    0.12
     вÑģп
    0.12
    coat
    0.12
    Activations Density 0.012%

    No Known Activations