© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 34177
    Prev
    Next
    INDEX
    Explanations

    wide range of

    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
    æŃ
    -0.10
     plethora
    -0.10
    âĹİ
    -0.10
     bunch
    -0.09
    ë¿IJ
    -0.09
    ILLE
    -0.09
    bish
    -0.09
    ãĤ£
    -0.09
    sei
    -0.09
    infeld
    -0.09
    POSITIVE LOGITS
     range
    0.20
     variety
    0.19
     number
    0.16
    vari
    0.12
     host
    0.12
    range
    0.12
    umber
    0.11
    number
    0.11
    Range
    0.10
     Range
    0.10
    Activations Density 0.011%

    No Known Activations