© 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. 20077
    Prev
    Next
    INDEX
    Explanations

    "I" offer to help

    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
    âĮĴ
    -0.09
     instruct
    -0.09
    umber
    -0.08
    ospels
    -0.08
     canopy
    -0.08
     muss
    -0.08
     Kew
    -0.08
    usz
    -0.08
    зна
    -0.08
    oba
    -0.08
    POSITIVE LOGITS
     happy
    0.35
    happy
    0.27
     Happy
    0.27
    Happy
    0.27
     willing
    0.23
     HAPP
    0.22
    åı¯ä»¥
    0.21
     could
    0.18
     can
    0.18
     feliz
    0.18
    Activations Density 0.124%

    No Known Activations