© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 35148
    Prev
    Next
    INDEX
    Explanations

    guidance and care

    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
     colleague
    -0.09
    .synthetic
    -0.09
    HF
    -0.09
    ãģ«ãģĬ
    -0.09
    anan
    -0.09
     neighb
    -0.09
     caret
    -0.09
    lyph
    -0.08
     upkeep
    -0.08
     Extended
    -0.08
    POSITIVE LOGITS
     supervision
    0.40
    çĽijçĿ£
    0.34
     Superv
    0.28
    çĽ£çĿ£
    0.24
     closely
    0.24
     oversight
    0.24
     guidance
    0.23
     superv
    0.22
     ê°IJëıħ
    0.22
    çĽij
    0.22
    Activations Density 0.101%

    No Known Activations