© 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. 900
    Prev
    Next
    INDEX
    Explanations

    specific nouns followed by states

    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
    627
    -0.10
     Ting
    -0.09
    erver
    -0.09
    yi
    -0.08
    ãģ«ãģĤãĤĭ
    -0.08
     Equals
    -0.08
     continu
    -0.08
    omm
    -0.08
     Hugh
    -0.08
    inges
    -0.08
    POSITIVE LOGITS
     occurred
    0.29
     occurs
    0.25
     occur
    0.24
     occured
    0.21
     came
    0.20
     happened
    0.20
    åıijçĶŁ
    0.19
    occ
    0.19
     ocor
    0.19
     erfol
    0.18
    Activations Density 0.106%

    No Known Activations