© 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. 20634
    Prev
    Next
    INDEX
    Explanations

    the noun phrase

    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
     DISCLAIM
    -0.10
     doorstep
    -0.09
    ÐĶÐļ
    -0.09
    dek
    -0.09
    ãĤīãģĹãģĦ
    -0.09
    eme
    -0.09
    ï½Ĭ
    -0.08
    ãĤĽ
    -0.08
    speaker
    -0.08
     incl
    -0.08
    POSITIVE LOGITS
     hope
    0.18
     absence
    0.18
     sense
    0.17
     form
    0.16
     hopes
    0.16
     spirit
    0.13
     manner
    0.13
    hope
    0.13
     meantime
    0.13
     context
    0.12
    Activations Density 0.082%

    No Known Activations