© 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. 17404
    Prev
    Next
    INDEX
    Explanations

    object or recipient of action

    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
     Ass
    -0.09
     Contrib
    -0.09
     Dil
    -0.09
     Tod
    -0.09
     gate
    -0.09
     IM
    -0.09
     sign
    -0.09
     cont
    -0.09
     thr
    -0.08
     priorities
    -0.08
    POSITIVE LOGITS
     object
    0.16
     receiver
    0.16
     receivers
    0.15
     passive
    0.15
     receiving
    0.15
     Passive
    0.14
     direct
    0.14
     acted
    0.13
     Direct
    0.13
     Receiver
    0.13
    Activations Density 0.099%

    No Known Activations