© 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. 45166
    Prev
    Next
    INDEX
    Explanations

    kind or type

    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
    å®ļçļĦ
    -0.09
    uba
    -0.09
    çļĦåľ°æĸ¹
    -0.09
    è¡¡
    -0.09
    çļĦæĥħåĨµ
    -0.09
     trait
    -0.09
     Trait
    -0.09
     amount
    -0.09
     Amount
    -0.08
    oge
    -0.08
    POSITIVE LOGITS
     nature
    0.32
    nature
    0.22
     origin
    0.22
     ilk
    0.21
     kind
    0.18
     vintage
    0.18
     Nature
    0.17
     consequence
    0.17
     magnitude
    0.17
    ilk
    0.16
    Activations Density 0.168%

    No Known Activations