© 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. 32298
    Prev
    Next
    INDEX
    Explanations

    assistant readies

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

    structured chat or dialogue formatting tokens, particularly those marking the transition between user input and assistant response.

    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
    apy
    -0.10
     ï¼ı:
    -0.10
    .IsNullOr
    -0.10
    entionPolicy
    -0.09
    .MixedReality
    -0.09
     jadx
    -0.09
    BeNull
    -0.08
     Trent
    -0.08
     Caller
    -0.08
    -Compatible
    -0.08
    POSITIVE LOGITS
    ok
    0.11
     гоÑĤов
    0.11
    гоÑĤов
    0.10
     DONE
    0.09
     ready
    0.09
     done
    0.09
     sẵn
    0.09
    )./
    0.09
     hostage
    0.09
    uju
    0.08
    Activations Density 0.066%

    No Known Activations