© 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. 30035
    Prev
    Next
    INDEX
    Explanations

    not present or available

    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
    ervas
    -0.09
     desper
    -0.09
    interop
    -0.09
    EFR
    -0.09
    (ok
    -0.08
    ToProps
    -0.08
    _passed
    -0.08
    woff
    -0.08
     unaffected
    -0.08
     Mey
    -0.08
    POSITIVE LOGITS
     present
    0.53
     presente
    0.34
    present
    0.33
     vorhand
    0.32
     Present
    0.32
    Present
    0.27
     presence
    0.27
    _present
    0.26
     présent
    0.26
    -present
    0.24
    Activations Density 0.115%

    No Known Activations