© 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
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 33866
    Prev
    Next
    INDEX
    Explanations

    locations and substances

    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
    727
    -0.09
     druž
    -0.09
     tieten
    -0.09
    _constants
    -0.09
     Jug
    -0.09
     sympath
    -0.09
     drown
    -0.09
    osg
    -0.09
    .stamp
    -0.08
     Pollution
    -0.08
    POSITIVE LOGITS
     soil
    0.16
     atmosphere
    0.15
     air
    0.15
     environment
    0.15
     water
    0.13
     bodies
    0.12
     drinking
    0.11
    çݯå¢ĥ
    0.11
    çĴ°å¢ĥ
    0.11
     ground
    0.11
    Activations Density 0.024%

    No Known Activations