© 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. 62936
    Prev
    Next
    INDEX
    Explanations

    predicted vs actual

    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
    odable
    -0.11
    965
    -0.09
     Powered
    -0.08
     Harper
    -0.08
     Gerr
    -0.08
    usu
    -0.08
     exponentially
    -0.08
    cheid
    -0.08
     waterproof
    -0.08
    nex
    -0.08
    POSITIVE LOGITS
     actual
    0.25
     Actual
    0.20
    actual
    0.19
    å®ŀéĻħ
    0.19
     reality
    0.18
    Actual
    0.18
    (actual
    0.16
     ìĭ¤ìłľ
    0.15
    Reality
    0.15
     atual
    0.15
    Activations Density 0.079%

    No Known Activations