© 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. 54073
    Prev
    Next
    INDEX
    Explanations

    approval of

    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
    ally
    -0.11
    inel
    -0.10
    uate
    -0.10
     dök
    -0.10
    ÑıÑħ
    -0.09
    yb
    -0.09
    ëĿ½
    -0.09
    ico
    -0.09
    orage
    -0.09
    chers
    -0.09
    POSITIVE LOGITS
    /legal
    0.12
    /lic
    0.12
    大åĪ©
    0.11
     duyá»ĩt
    0.10
    ilon
    0.10
    /license
    0.10
    /sign
    0.10
    /dis
    0.10
    /app
    0.10
    Stamp
    0.10
    Activations Density 0.025%

    No Known Activations