© 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. 54466
    Prev
    Next
    INDEX
    Explanations

    user prefixes

    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
     undermin
    -0.09
    chor
    -0.09
     âĺĨ
    -0.08
    ζα
    -0.08
    527
    -0.08
    ε
    -0.08
    apest
    -0.08
    xis
    -0.08
    ovah
    -0.08
     Highlander
    -0.08
    POSITIVE LOGITS
     Boeh
    0.08
    Ùij
    0.08
    olina
    0.08
     Tribe
    0.08
     associative
    0.08
     Arb
    0.08
    iday
    0.08
    rescia
    0.08
    nf
    0.08
    idy
    0.07
    Activations Density 0.167%

    No Known Activations