© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 13852
    Prev
    Next
    INDEX
    Explanations

    then followed by specific words

    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
    stateParams
    -0.11
    ilion
    -0.10
    alion
    -0.09
    ,None
    -0.09
    .mem
    -0.08
     whe
    -0.08
     Hi
    -0.08
    engin
    -0.08
    ëĿ¼ëĬĶ
    -0.08
     -*-č\n
    -0.08
    POSITIVE LOGITS
    dap
    0.09
    ensch
    0.09
    odore
    0.08
    prak
    0.08
    ãģ¾ãģļ
    0.08
    elop
    0.08
    nown
    0.08
    MOTE
    0.08
    olf
    0.08
    å¾Ĵ
    0.07
    Activations Density 0.183%

    No Known Activations