© 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. 13071
    Prev
    Next
    INDEX
    Explanations

    incoming and outgoing

    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
    ahoo
    -0.10
    æ´¥
    -0.10
     Invent
    -0.09
    _processing
    -0.09
    .communic
    -0.09
    oken
    -0.08
    grese
    -0.08
     Passing
    -0.08
     bearer
    -0.08
     carrier
    -0.08
    POSITIVE LOGITS
     receiving
    0.16
     outgoing
    0.15
     reverse
    0.15
     receive
    0.15
     both
    0.14
     bid
    0.14
     incoming
    0.14
     outbound
    0.13
    éĢĨ
    0.13
     input
    0.13
    Activations Density 0.240%

    No Known Activations