© 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. 1864
    Prev
    Next
    INDEX
    Explanations

    purification steps and methods

    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
    awe
    -0.10
     Decom
    -0.09
    udit
    -0.09
    pong
    -0.09
    .TypeOf
    -0.09
    ÎķÎļ
    -0.09
    elage
    -0.09
     Progressive
    -0.09
     decom
    -0.08
     Neo
    -0.08
    POSITIVE LOGITS
     techniques
    0.23
     technique
    0.20
     methods
    0.16
     Techniques
    0.15
     separation
    0.15
     physical
    0.14
     process
    0.13
     Physical
    0.13
     column
    0.13
    Physical
    0.13
    Activations Density 0.009%

    No Known Activations