© 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. 31520
    Prev
    Next
    INDEX
    Explanations

    orphan or rare interest

    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
     Persona
    -0.10
     Pry
    -0.10
     Dimit
    -0.09
    æĨ¶
    -0.09
    _te
    -0.09
     medic
    -0.09
     Kore
    -0.09
     å£
    -0.09
     adm
    -0.09
    ooth
    -0.09
    POSITIVE LOGITS
     orphan
    0.24
    phan
    0.17
     Rare
    0.16
     rare
    0.15
     Or
    0.15
    Rare
    0.14
     IND
    0.13
     rarity
    0.13
     sponsor
    0.12
    orph
    0.11
    Activations Density 0.004%

    No Known Activations