© 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. 3025
    Prev
    Next
    INDEX
    Explanations

    return or back

    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
     frontend
    -0.15
    frontend
    -0.15
    Backup
    -0.15
    /frontend
    -0.14
     Backup
    -0.14
     Front
    -0.13
    Backing
    -0.13
    _frontend
    -0.12
     ãĢī
    -0.12
    Front
    -0.11
    POSITIVE LOGITS
     back
    1.04
     zurück
    0.66
    back
    0.64
    _back
    0.55
     terug
    0.55
     zpÄĽt
    0.54
    -back
    0.54
    .back
    0.52
    Back
    0.52
     BACK
    0.49
    Activations Density 0.140%

    No Known Activations