© 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. 13801
    Prev
    Next
    INDEX
    Explanations

    n events, their levels, particular class

    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
    pairs
    -0.11
     Classification
    -0.10
     Hull
    -0.10
    oux
    -0.10
    Classification
    -0.10
    елÑı
    -0.09
    |/
    -0.09
    RuleContext
    -0.09
    zeros
    -0.09
     åı¸
    -0.09
    POSITIVE LOGITS
     possible
    0.25
     classes
    0.21
     Possible
    0.20
    possible
    0.18
    Possible
    0.17
     possibile
    0.16
     categories
    0.16
     distinct
    0.15
     Classes
    0.15
     possÃŃvel
    0.15
    Activations Density 0.175%

    No Known Activations