© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 1796
    Prev
    Next
    INDEX
    Explanations

    baseline scenario for comparison

    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
    lez
    -0.12
     unsupported
    -0.09
     Nur
    -0.08
    bih
    -0.08
    ymb
    -0.08
    unker
    -0.08
    chip
    -0.08
    etections
    -0.08
    antas
    -0.08
    usta
    -0.08
    POSITIVE LOGITS
     reference
    0.53
    reference
    0.41
     Reference
    0.40
     benchmark
    0.37
     baseline
    0.36
    Reference
    0.35
    -reference
    0.35
     comparison
    0.33
    (reference
    0.31
     referencia
    0.31
    Activations Density 0.182%

    No Known Activations