© 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. 59908
    Prev
    Next
    INDEX
    Explanations

    preventing negative outcomes

    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
    ollo
    -0.10
     careless
    -0.10
     Bauer
    -0.09
    ẹp
    -0.09
    ilded
    -0.09
    ugal
    -0.08
    -cond
    -0.08
    анÑĮ
    -0.08
    stor
    -0.08
     Glo
    -0.08
    POSITIVE LOGITS
     further
    0.16
     spread
    0.15
     becoming
    0.13
     harm
    0.12
     damage
    0.12
     access
    0.12
     далÑĮней
    0.12
     future
    0.12
     Spread
    0.11
     anymore
    0.11
    Activations Density 0.063%

    No Known Activations