© 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. 21224
    Prev
    Next
    INDEX
    Explanations

    leading to damage or decline

    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
     RID
    -0.09
    XE
    -0.09
     поба
    -0.09
    uyá»ĩt
    -0.09
    vest
    -0.09
     showdown
    -0.09
    insky
    -0.09
     Sou
    -0.09
     paras
    -0.08
    cj
    -0.08
    POSITIVE LOGITS
     Damage
    0.12
    Damage
    0.12
     cascade
    0.11
     inex
    0.11
     leading
    0.11
     vicious
    0.11
     leads
    0.11
     unchecked
    0.10
     dys
    0.10
     resulting
    0.10
    Activations Density 0.070%

    No Known Activations