© 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. 17579
    Prev
    Next
    INDEX
    Explanations

    as an ai language

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

    special tokens marking the boundary between user and assistant turns in a chat conversation format.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @yooniel31
    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
     Malk
    -0.09
    logan
    -0.09
    DNA
    -0.09
    affer
    -0.09
    onet
    -0.08
    inecraft
    -0.08
    ãĥ
    -0.08
    odic
    -0.08
    usra
    -0.08
    OffsetTable
    -0.08
    POSITIVE LOGITS
    ä½ľä¸º
    0.14
     tôi
    0.11
     sebagai
    0.10
     myself
    0.10
     Chat
    0.10
     software
    0.10
     jako
    0.09
     as
    0.09
     being
    0.09
     Software
    0.09
    Activations Density 0.156%

    No Known Activations