© 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. 38808
    Prev
    Next
    INDEX
    Explanations

    "The" followed by a noun introducing a concept

    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
     attendant
    -0.09
    occo
    -0.09
     presum
    -0.08
     ores
    -0.08
    _IMPL
    -0.08
    677
    -0.08
    aims
    -0.08
     resultant
    -0.08
     *);\n\n
    -0.08
    TED
    -0.08
    POSITIVE LOGITS
     reason
    0.22
     fact
    0.18
    oret
    0.16
     reasons
    0.15
     presence
    0.14
     only
    0.13
     key
    0.13
     answer
    0.13
     reasoning
    0.13
     statement
    0.13
    Activations Density 0.060%

    No Known Activations