© 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. 12075
    Prev
    Next
    INDEX
    Explanations

    end of sentence or explanation

    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
     Shake
    -0.13
     shaking
    -0.10
     shake
    -0.10
     shakes
    -0.10
     Gore
    -0.09
    olas
    -0.09
    ï¾ŀï¾ŀ
    -0.09
    shake
    -0.09
     Hansen
    -0.09
    836
    -0.08
    POSITIVE LOGITS
     no
    0.24
     wait
    0.20
     False
    0.17
     FALSE
    0.17
     false
    0.17
    no
    0.16
     Wait
    0.15
    Wait
    0.15
     неÑĤ
    0.15
    FALSE
    0.15
    Activations Density 0.079%

    No Known Activations