© 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. 56595
    Prev
    Next
    INDEX
    Explanations

    noxious opinion, budding smile, fiendish demon

    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
    •GENERAL
    •GOBLIN

    No Comments

    Negative Logits
    ¶Į
    -0.10
    irit
    -0.09
    ******č\n
    -0.08
    erk
    -0.08
     Ace
    -0.08
    ¯u
    -0.08
    ãģ®ãģł
    -0.08
     Halk
    -0.07
    ıa
    -0.07
    924
    -0.07
    POSITIVE LOGITS
     {?}
    0.09
     VÅ¡ech
    0.08
     GIVEN
    0.08
    /of
    0.08
    -of
    0.08
    ofday
    0.08
     [=
    0.08
    -looking
    0.08
    çĶ·åŃIJ
    0.08
     kariy
    0.08
    Activations Density 0.328%

    No Known Activations