© 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. 56881
    Prev
    Next
    INDEX
    Explanations

    model output quality

    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
    ayan
    -0.09
     chants
    -0.09
    "data
    -0.08
    plode
    -0.08
    æĥł
    -0.08
     env
    -0.08
    ³ç´°
    -0.08
     yapım
    -0.08
    lash
    -0.08
    ¶Į
    -0.08
    POSITIVE LOGITS
     output
    0.35
     generated
    0.31
     Output
    0.27
     outputs
    0.26
     produced
    0.26
    output
    0.25
    è¾ĵåĩº
    0.24
    Output
    0.23
    generated
    0.22
     Generated
    0.21
    Activations Density 0.149%

    No Known Activations