© 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. 34823
    Prev
    Next
    INDEX
    Explanations

    finding items matching conditions

    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
    itial
    -0.10
     forbidden
    -0.10
     Meadow
    -0.10
     oppos
    -0.09
     EACH
    -0.09
    ernal
    -0.09
     nou
    -0.09
     Bark
    -0.09
    ellen
    -0.09
     Butt
    -0.09
    POSITIVE LOGITS
     whose
    0.23
    whose
    0.18
     matching
    0.17
     Matching
    0.15
    Matching
    0.14
    matching
    0.14
     à¤ľà¤¹
    0.11
     nÃło
    0.11
     where
    0.10
     fitting
    0.10
    Activations Density 0.108%

    No Known Activations