© 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. 54446
    Prev
    Next
    INDEX
    Explanations

    average quantities or typical states

    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
     âĨIJ
    -0.09
     bestellen
    -0.09
    ather
    -0.09
    buzz
    -0.08
    argin
    -0.08
    amerate
    -0.08
     lik
    -0.08
     inval
    -0.08
     Sachs
    -0.08
     buzz
    -0.08
    POSITIVE LOGITS
     average
    0.23
     typical
    0.22
    average
    0.19
     prices
    0.18
    å¹³åĿĩ
    0.17
     depending
    0.16
    typ
    0.16
     typically
    0.16
     Average
    0.15
    Average
    0.15
    Activations Density 0.109%

    No Known Activations