© 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. 20401
    Prev
    Next
    INDEX
    Explanations

    tailored CRM insights

    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
     Mell
    -0.11
     Cara
    -0.09
     lateral
    -0.09
     Carlton
    -0.09
    venience
    -0.09
     Garland
    -0.09
    avigation
    -0.09
     Sv
    -0.08
     chÃŃ
    -0.08
     Eck
    -0.08
    POSITIVE LOGITS
     CRM
    0.28
    CRM
    0.24
    crm
    0.22
     sales
    0.22
    .crm
    0.21
     Sales
    0.20
     CR
    0.20
     cr
    0.19
     lead
    0.19
    Sales
    0.19
    Activations Density 0.075%

    No Known Activations