© 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. 63602
    Prev
    Next
    INDEX
    Explanations

    had also been

    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
     Dub
    -0.10
     impro
    -0.09
     curse
    -0.09
     Coy
    -0.09
    .DataBind
    -0.09
    âī§
    -0.08
     dying
    -0.08
    ault
    -0.08
     Arn
    -0.08
     never
    -0.08
    POSITIVE LOGITS
     isolated
    0.18
     isol
    0.17
     isolate
    0.17
     alien
    0.16
     isolation
    0.16
     increasingly
    0.16
    alien
    0.15
     spiral
    0.14
    isol
    0.14
     become
    0.14
    Activations Density 0.035%

    No Known Activations