© 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. 8818
    Prev
    Next
    INDEX
    Explanations

    prefixes and common suffixes

    np_acts-logits-general · gemini-2.5-flash-lite

    formal, domain-specific language—especially medical/legal/technical jargon and capitalized acronyms or CamelCase tokens indicative of institutional or technical contexts.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
     %[
    -0.09
     autogenerated
    -0.08
    efeller
    -0.08
    _equalTo
    -0.07
    yleft
    -0.07
    eldo
    -0.07
     [âĢ¦
    -0.07
    ï¿
    -0.07
    exampleInput
    -0.07
    .opensource
    -0.07
    POSITIVE LOGITS
    ÂŃing
    0.10
    &apos
    0.09
    ฺ
    0.08
     ¶
    0.08
    ÂŃs
    0.08
    ?#
    0.07
    ÂŃi
    0.07
    mps
    0.07
    zens
    0.07
    ÂŃt
    0.07
    Activations Density 5.193%

    No Known Activations