© 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. 43653
    Prev
    Next
    INDEX
    Explanations

    the desired / the following steps

    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
     Verfüg
    -0.10
     interim
    -0.10
    è°
    -0.10
    uta
    -0.10
     breakdown
    -0.09
    876
    -0.09
    assen
    -0.09
    ucker
    -0.08
    Bearer
    -0.08
     stable
    -0.08
    POSITIVE LOGITS
    quiv
    0.12
     reflux
    0.11
     diary
    0.11
     McN
    0.10
     Corey
    0.10
    Entries
    0.10
    Protocol
    0.10
     Me
    0.10
     Conditions
    0.10
     displacement
    0.10
    Activations Density 0.015%

    No Known Activations