© 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. 60907
    Prev
    Next
    INDEX
    Explanations

    MIDI files or subtraction

    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
     Continue
    -0.10
    ynes
    -0.08
     mastur
    -0.08
    oldur
    -0.08
    ught
    -0.07
     Geile
    -0.07
     bÄĥng
    -0.07
     VÅ¡ech
    -0.07
     legit
    -0.07
    owitz
    -0.07
    POSITIVE LOGITS
     vibr
    0.08
    occo
    0.07
    éŀ
    0.07
    deo
    0.07
    inux
    0.07
    [rand
    0.07
    ForMember
    0.07
     Lever
    0.07
    _mime
    0.07
    Sharper
    0.07
    Activations Density 0.099%

    No Known Activations