© 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. 34465
    Prev
    Next
    INDEX
    Explanations

    following instructions or terms of service

    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
    zer
    -0.09
    renched
    -0.09
    $MESS
    -0.09
     Cecil
    -0.09
    iks
    -0.08
    ewire
    -0.08
    uitka
    -0.08
     Kerry
    -0.08
     Kern
    -0.08
    oyal
    -0.08
    POSITIVE LOGITS
     provided
    0.23
    provided
    0.18
     Provided
    0.16
     offered
    0.15
     supplied
    0.14
     furnished
    0.13
     accompanying
    0.13
     ìłľê³µ
    0.13
     forn
    0.13
     specific
    0.12
    Activations Density 0.053%

    No Known Activations