© 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. 31714
    Prev
    Next
    INDEX
    Explanations

    be particularly, could take, depending on

    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
     cannot
    -0.12
    Cannot
    -0.11
     Cannot
    -0.10
     inc
    -0.10
     assim
    -0.10
    cannot
    -0.10
     Duch
    -0.10
     perfect
    -0.09
     Perfect
    -0.09
     nast
    -0.09
    POSITIVE LOGITS
     fairly
    0.14
     -*-č\n
    0.13
     somewhat
    0.12
    łéĻ¤
    0.11
    ÂĢÂĢ
    0.10
    ¶Į
    0.10
    deniz
    0.09
    ebek
    0.09
     definitely
    0.09
    ******č\n
    0.09
    Activations Density 0.007%

    No Known Activations