© 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. 42446
    Prev
    Next
    INDEX
    Explanations

    bright followed by adjectives or 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
    abbrev
    -0.10
    itarian
    -0.10
    hay
    -0.09
    ably
    -0.09
    ately
    -0.09
    abwe
    -0.09
    anine
    -0.08
     velvet
    -0.08
     fro
    -0.08
    ￣￣
    -0.08
    POSITIVE LOGITS
    ening
    0.33
    ened
    0.29
    eners
    0.19
    en
    0.17
    ens
    0.17
    ener
    0.17
    enin
    0.16
    er
    0.16
    -eyed
    0.14
    s
    0.13
    Activations Density 0.020%

    No Known Activations