© 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. 51078
    Prev
    Next
    INDEX
    Explanations

    message information and content

    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
     mailing
    -0.11
     emailing
    -0.10
    Ctrls
    -0.10
    Mailer
    -0.09
    SHARE
    -0.09
    ãĥĭãĥĭ
    -0.09
    åħ
    -0.09
    _requested
    -0.09
    Tac
    -0.09
    .updateDynamic
    -0.09
    POSITIVE LOGITS
     conversation
    0.22
     messages
    0.20
     conversations
    0.20
     Conversation
    0.18
     threads
    0.17
    Conversation
    0.17
     convers
    0.16
     Convers
    0.16
     thread
    0.16
     Messages
    0.16
    Activations Density 0.154%

    No Known Activations