© 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. 15515
    Prev
    Next
    INDEX
    Explanations

    inseminate or find suitable donor

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

    procedural, step-by-step instructions in imperative form, especially within numbered lists.

    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
     antioxid
    -0.10
     Platt
    -0.10
     reim
    -0.09
     drunken
    -0.09
     illicit
    -0.09
     Vacc
    -0.09
     cigaret
    -0.09
     channel
    -0.09
     nicotine
    -0.09
    agina
    -0.09
    POSITIVE LOGITS
    åīĤ
    0.16
     Roh
    0.14
     Roof
    0.14
     knockout
    0.13
     dr
    0.13
     agent
    0.12
     dos
    0.12
     sed
    0.12
     spiked
    0.12
    åĤ¬
    0.12
    Activations Density 0.104%

    No Known Activations