© 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. 37095
    Prev
    Next
    INDEX
    Explanations

    harmful or illegal content

    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
    (æľĪ
    -0.10
    ãİ
    -0.10
    engkap
    -0.10
    ëıĦë³Ħ
    -0.08
    "';
    -0.08
    rupted
    -0.08
    aData
    -0.08
    tract
    -0.08
    Verdana
    -0.08
    ORIZED
    -0.08
    POSITIVE LOGITS
     hurt
    0.10
     content
    0.10
     vul
    0.09
     violence
    0.09
     bundled
    0.08
     harm
    0.08
    inh
    0.08
    301
    0.08
     Content
    0.08
     potentially
    0.08
    Activations Density 0.054%

    No Known Activations