© 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. 57005
    Prev
    Next
    INDEX
    Explanations

    eco-friendly actions list

    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
    ibox
    -0.10
    _BB
    -0.10
     safety
    -0.09
     Borg
    -0.09
     rein
    -0.08
    715
    -0.08
     Flames
    -0.08
    afety
    -0.08
     Rot
    -0.08
     Affordable
    -0.08
    POSITIVE LOGITS
     offset
    0.15
     Meat
    0.14
     Offset
    0.14
     Plastic
    0.12
     carbon
    0.12
    -offset
    0.12
     choices
    0.12
     switch
    0.12
     meat
    0.12
     offsets
    0.12
    Activations Density 0.056%

    No Known Activations