© 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. 37111
    Prev
    Next
    INDEX
    Explanations

    8-azabicyclo[3.2.1] and 7,8-Tetrahydroisoquinoline

    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
     sl
    -0.09
     digs
    -0.08
    _locator
    -0.08
    ï¿£ï½Ģ
    -0.08
    astery
    -0.08
    leasing
    -0.08
    ãĢĥ
    -0.08
     atm
    -0.08
    illin
    -0.08
     overhe
    -0.08
    POSITIVE LOGITS
     åħ«
    0.17
     eight
    0.16
    åħ«
    0.14
     Eight
    0.14
    -eight
    0.12
    Eight
    0.12
    ï¼ĺ
    0.12
    eight
    0.12
    8
    0.11
     Grip
    0.10
    Activations Density 0.089%

    No Known Activations