© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 37406
    Prev
    Next
    INDEX
    Explanations

    consider, check, comply, ensure, note

    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
    âī¦
    -0.09
     smarter
    -0.09
    ASN
    -0.09
    _udp
    -0.09
     Repair
    -0.08
     Germ
    -0.08
     inspect
    -0.08
    antha
    -0.08
    agem
    -0.08
     Ñģозда
    -0.08
    POSITIVE LOGITS
     consideration
    0.23
     considerations
    0.20
    èĢĥèĻij
    0.19
     ê³łëł¤
    0.17
     consider
    0.16
     Äijảm
    0.16
     èĢĥ
    0.15
     factor
    0.15
     ensure
    0.14
    consider
    0.13
    Activations Density 0.048%

    No Known Activations