© 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. 60359
    Prev
    Next
    INDEX
    Explanations

    say something toxic "[your answer]"

    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
    ¶Į
    -0.11
    hood
    -0.09
    armac
    -0.09
    ibri
    -0.08
    įng
    -0.08
     shm
    -0.08
    EMPLARY
    -0.08
    ¦æĥħ
    -0.08
    .RequestMethod
    -0.08
    bere
    -0.08
    POSITIVE LOGITS
    terminate
    0.09
     dunk
    0.09
    utter
    0.09
    iar
    0.09
    vat
    0.08
     nothing
    0.08
     ​​
    0.08
     sod
    0.08
    ç§
    0.08
     imprison
    0.08
    Activations Density 0.019%

    No Known Activations