© 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. 34417
    Prev
    Next
    INDEX
    Explanations

    track record

    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
    aries
    -0.10
    inke
    -0.10
    ously
    -0.10
    alties
    -0.10
    cue
    -0.10
    akash
    -0.09
    airy
    -0.09
    orest
    -0.09
    er
    -0.09
    oksen
    -0.09
    POSITIVE LOGITS
     record
    0.20
    side
    0.17
    -record
    0.16
    record
    0.15
     Record
    0.14
     track
    0.13
    (track
    0.13
    .Track
    0.13
    Record
    0.13
    lements
    0.13
    Activations Density 0.005%

    No Known Activations