© 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. 27030
    Prev
    Next
    INDEX
    Explanations

    risk and its management

    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
    /read
    -0.10
    ally
    -0.10
    agn
    -0.09
    orado
    -0.09
     risking
    -0.09
    ESS
    -0.09
     Ryu
    -0.08
    unn
    -0.08
    bred
    -0.08
    گاÙĩÛĮ
    -0.08
    POSITIVE LOGITS
    iest
    0.21
    iness
    0.19
    ier
    0.18
    ed
    0.15
     factors
    0.13
    -taking
    0.12
    ily
    0.12
     appetite
    0.11
    averse
    0.11
    éĻº
    0.11
    Activations Density 0.015%

    No Known Activations