© 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. 64269
    Prev
    Next
    INDEX
    Explanations

    ideal and its forms

    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
    <|begin_of_text|>
    -0.13
    es
    -0.11
    ets
    -0.11
     âĨĴ\n\n
    -0.10
    elo
    -0.10
    emouth
    -0.09
    atis
    -0.09
    atak
    -0.09
    anje
    -0.09
    ello
    -0.09
    POSITIVE LOGITS
    ized
    0.29
    istic
    0.27
    istically
    0.21
    ogy
    0.20
    ised
    0.20
    izations
    0.18
    ization
    0.18
    ities
    0.17
    ogue
    0.16
    ize
    0.15
    Activations Density 0.018%

    No Known Activations