© 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. 36006
    Prev
    Next
    INDEX
    Explanations

    pose potential risks

    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
    kul
    -0.09
     dele
    -0.09
    cul
    -0.09
    EO
    -0.09
    verity
    -0.09
    oba
    -0.09
    à¸ļาล
    -0.08
    kaar
    -0.08
    hardt
    -0.08
    ither
    -0.08
    POSITIVE LOGITS
     raise
    0.23
    pose
    0.22
    Pose
    0.22
     raises
    0.21
    poses
    0.20
     Pose
    0.20
     presents
    0.20
     pose
    0.19
     carry
    0.19
    POSE
    0.19
    Activations Density 0.086%

    No Known Activations