© 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. 40938
    Prev
    Next
    INDEX
    Explanations

    checking settings, 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
     Cla
    -0.10
     asylum
    -0.09
     mar
    -0.09
    ÑĢава
    -0.09
     scenarios
    -0.08
     Kai
    -0.08
     Claus
    -0.08
    937
    -0.08
    elles
    -0.08
     Hanson
    -0.08
    POSITIVE LOGITS
     go
    0.16
     goto
    0.15
     follow
    0.14
     open
    0.14
     Open
    0.13
     steps
    0.13
    Open
    0.13
    Go
    0.13
    Steps
    0.12
     Go
    0.12
    Activations Density 0.101%

    No Known Activations