© 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. 60523
    Prev
    Next
    INDEX
    Explanations

    minutes away from

    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
     pedestrian
    -0.10
    éĻĦè¿ij
    -0.09
     cru
    -0.09
     Mister
    -0.08
     fizz
    -0.08
    ffa
    -0.08
    runner
    -0.08
    isle
    -0.08
     downgrade
    -0.08
     nearby
    -0.08
    POSITIVE LOGITS
     drive
    0.28
    drive
    0.20
     Drive
    0.18
     ride
    0.18
     drives
    0.17
    -drive
    0.16
     hour
    0.16
     short
    0.15
    Drive
    0.15
    _drive
    0.14
    Activations Density 0.040%

    No Known Activations