© 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. 37873
    Prev
    Next
    INDEX
    Explanations

    introducing a point

    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
    olle
    -0.10
     lez
    -0.09
     Bund
    -0.09
    enberg
    -0.09
    under
    -0.09
    \common
    -0.08
    ritic
    -0.08
    éģ£
    -0.08
    akis
    -0.08
     slapped
    -0.08
    POSITIVE LOGITS
     know
    0.14
     stress
    0.12
     point
    0.11
     offer
    0.11
     state
    0.10
     cord
    0.10
     note
    0.10
     add
    0.10
     hum
    0.10
     Arb
    0.10
    Activations Density 0.045%

    No Known Activations