© 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. 25657
    Prev
    Next
    INDEX
    Explanations

    code identifiers or types

    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
    aison
    -0.09
    å¯Ĵ
    -0.08
    iland
    -0.08
    rove
    -0.08
     Swe
    -0.08
     ä¸ĢèĪ¬
    -0.07
     Lav
    -0.07
    iao
    -0.07
    ynth
    -0.07
    оÑĢÑĥ
    -0.07
    POSITIVE LOGITS
    /-
    0.11
    AndPassword
    0.10
    yles
    0.09
    âĢ¬
    0.09
    @yahoo
    0.08
    AGEMENT
    0.08
    ahl
    0.08
    ÂŃi
    0.08
    urope
    0.08
     Guzzle
    0.08
    Activations Density 0.114%

    No Known Activations