© 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. 35940
    Prev
    Next
    INDEX
    Explanations

    magnetic field, magnetism, strip

    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
     magnets
    -0.09
    antis
    -0.09
     electronics
    -0.09
    ilit
    -0.09
     Vz
    -0.08
    ibble
    -0.08
    å¼ĭ
    -0.08
    ÑŁ
    -0.08
     phạm
    -0.08
    اء
    -0.08
    POSITIVE LOGITS
     field
    0.17
    -field
    0.16
     Lev
    0.14
     fields
    0.14
    field
    0.13
     flux
    0.12
    ificent
    0.12
    ically
    0.12
    /opt
    0.12
    Field
    0.12
    Activations Density 0.021%

    No Known Activations