© 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. 59919
    Prev
    Next
    INDEX
    Explanations

    -based suffixes with nouns

    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
    -derived
    -0.19
    -inspired
    -0.17
    -wide
    -0.15
    -produced
    -0.15
    -specific
    -0.15
    -generated
    -0.15
    -associated
    -0.15
    -mounted
    -0.15
    -independent
    -0.14
    -style
    -0.13
    POSITIVE LOGITS
     rich
    0.25
    -rich
    0.24
    rich
    0.20
    -l
    0.19
    ridden
    0.18
    laden
    0.18
     intensive
    0.18
     ridden
    0.18
     Rich
    0.16
    Rich
    0.16
    Activations Density 0.351%

    No Known Activations