© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 43726
    Prev
    Next
    INDEX
    Explanations

    legal and health consequences

    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
     economical
    -0.08
    jiang
    -0.08
     narciss
    -0.08
     Interracial
    -0.08
    ikon
    -0.08
     Lantern
    -0.08
    okin
    -0.08
     Ballard
    -0.08
     Slut
    -0.08
    _REF
    -0.08
    POSITIVE LOGITS
     chem
    0.12
     legal
    0.10
     pyt
    0.10
     intr
    0.10
     Chem
    0.10
     disarm
    0.10
    JD
    0.10
     Rica
    0.10
     safer
    0.09
     inhal
    0.09
    Activations Density 0.005%

    No Known Activations