© 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. 4554
    Prev
    Next
    INDEX
    Explanations

    underlying structure

    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
     stochastic
    -0.11
     pec
    -0.09
    raman
    -0.09
    asa
    -0.09
    .removeAttribute
    -0.09
    nier
    -0.08
    |=\n
    -0.08
     bibli
    -0.08
     AMA
    -0.08
     ç²
    -0.08
    POSITIVE LOGITS
     underlying
    0.23
     true
    0.19
     distribution
    0.18
    true
    0.16
     population
    0.15
     unknown
    0.15
     distributions
    0.13
     Distribution
    0.13
    distribution
    0.13
    istribution
    0.13
    Activations Density 0.095%

    No Known Activations