© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 35580
    Prev
    Next
    INDEX
    Explanations

    ground or floor

    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
    .:.
    -0.11
    дина
    -0.10
    orgh
    -0.09
    omu
    -0.09
    ube
    -0.09
    ì¢Į
    -0.09
    vla
    -0.08
     Precision
    -0.08
    ÑĤин
    -0.08
    954
    -0.08
    POSITIVE LOGITS
     ground
    0.80
    ground
    0.60
     floor
    0.55
     Ground
    0.51
    Ground
    0.51
    -ground
    0.49
    _ground
    0.48
     Floor
    0.44
    GROUND
    0.43
    floor
    0.42
    Activations Density 0.091%

    No Known Activations