© 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. 31219
    Prev
    Next
    INDEX
    Explanations

    instructions to use specific words or avoid them

    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
    .scalablytyped
    -0.09
    ardless
    -0.09
    GGLE
    -0.09
    éŀ
    -0.08
    zza
    -0.08
    æĭĶ
    -0.08
     kilomet
    -0.08
    antha
    -0.08
    aris
    -0.08
    .timeScale
    -0.08
    POSITIVE LOGITS
     Incre
    0.09
    udem
    0.09
     Wyn
    0.09
    __$
    0.08
    ently
    0.08
     (*((
    0.08
     stunt
    0.08
    .hw
    0.08
    tant
    0.08
    alion
    0.08
    Activations Density 0.094%

    No Known Activations