© 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. 36928
    Prev
    Next
    INDEX
    Explanations

    piper, pyridine, pantothenic

    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
    op
    -0.13
    opa
    -0.12
    arse
    -0.11
    osc
    -0.10
    ulse
    -0.10
    red
    -0.10
    age
    -0.10
    ete
    -0.10
    ok
    -0.10
    aper
    -0.10
    POSITIVE LOGITS
    oy
    0.13
    اÙĪرپ
    0.12
    ental
    0.12
    angen
    0.11
    anto
    0.11
    ome
    0.11
    rid
    0.11
    omo
    0.10
     orbital
    0.10
    iro
    0.10
    Activations Density 0.056%

    No Known Activations