© 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. 62522
    Prev
    Next
    INDEX
    Explanations

    states or what will happen

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

    abstract nouns representing concepts, ideas, or states of being.

    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
     seems
    -0.13
     seem
    -0.11
     लà¤Ĺत
    -0.11
    ABI
    -0.11
     semble
    -0.11
     seemed
    -0.10
     remains
    -0.10
     parece
    -0.10
    abi
    -0.10
    pare
    -0.10
    POSITIVE LOGITS
     will
    0.13
     sẽ
    0.10
     actually
    0.10
     itself
    0.10
     represents
    0.10
     represent
    0.10
     might
    0.10
     sia
    0.10
    ä¹ĥ
    0.10
    enk
    0.09
    Activations Density 0.079%

    No Known Activations