© 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. 23446
    Prev
    Next
    INDEX
    Explanations

    you would like me to

    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
     erotische
    -0.10
    -regexp
    -0.09
     GLUT
    -0.09
     \č\n
    -0.09
     eigentlich
    -0.08
    clud
    -0.08
    ï¾ij
    -0.08
     SHALL
    -0.08
     actually
    -0.08
    .fhir
    -0.08
    POSITIVE LOGITS
     probably
    0.14
     may
    0.14
     sometimes
    0.12
     perhaps
    0.11
    may
    0.11
     maybe
    0.11
     might
    0.11
     peut
    0.11
     busy
    0.10
     może
    0.10
    Activations Density 0.069%

    No Known Activations