© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 2405
    Prev
    Next
    INDEX
    Explanations

    chemical compound odors

    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
    abcdefgh
    -0.09
    izens
    -0.09
    pst
    -0.08
    izen
    -0.08
     reb
    -0.08
     merry
    -0.08
    ABCDEFGHI
    -0.08
    Registers
    -0.08
    abcdefghijkl
    -0.08
     UNSIGNED
    -0.08
    POSITIVE LOGITS
     molecular
    0.27
     melting
    0.22
     Molecular
    0.21
    olecular
    0.16
     boiling
    0.16
     formula
    0.15
     molec
    0.15
     CAS
    0.13
     Formula
    0.13
     purity
    0.13
    Activations Density 0.033%

    No Known Activations