© 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. 1534
    Prev
    Next
    INDEX
    Explanations

    permitted disallowed bringing

    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
    è¿«
    -0.11
     disin
    -0.10
     kims
    -0.10
     hum
    -0.09
     shut
    -0.09
     targets
    -0.09
    andan
    -0.09
     oversight
    -0.08
    æĪ¸
    -0.08
     bes
    -0.08
    POSITIVE LOGITS
     allowed
    0.14
     Allowed
    0.14
    Allowed
    0.14
     bring
    0.13
    带
    0.13
     Solic
    0.13
     prohibited
    0.13
     bringing
    0.13
     permitted
    0.13
    allowed
    0.13
    Activations Density 0.086%

    No Known Activations