© 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. 39739
    Prev
    Next
    INDEX
    Explanations

    actions to comply submit provide

    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
    sted
    -0.10
    protected
    -0.10
     Anth
    -0.09
     protected
    -0.09
     Pru
    -0.09
     insensitive
    -0.08
     rais
    -0.08
    à¸Ļà¹ĥà¸Ī
    -0.08
     anth
    -0.08
     assistance
    -0.08
    POSITIVE LOGITS
     training
    0.12
    åŁ¹è®Ń
    0.11
    -training
    0.11
     properly
    0.11
     design
    0.11
     provided
    0.10
     proper
    0.10
     provide
    0.10
     Label
    0.10
     label
    0.10
    Activations Density 0.010%

    No Known Activations