© 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. 15685
    Prev
    Next
    INDEX
    Explanations

    left and right directions

    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
    py
    -0.09
     southwestern
    -0.09
    ToUpper
    -0.09
     Schwarz
    -0.08
    fdb
    -0.08
    bread
    -0.08
    403
    -0.08
    ÛĮاÙĨ
    -0.08
     eyeb
    -0.08
    tein
    -0.08
    POSITIVE LOGITS
     left
    0.37
     right
    0.27
    å·¦
    0.26
    left
    0.25
     Left
    0.20
    _left
    0.20
    åı³
    0.20
     LEFT
    0.20
    Left
    0.19
    \tleft
    0.19
    Activations Density 0.069%

    No Known Activations