© 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. 43365
    Prev
    Next
    INDEX
    Explanations

    chemical industry applications

    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
    ＿_
    -0.09
    ¶Į
    -0.09
    ãģĹãģŁãĤī
    -0.08
     Erotik
    -0.08
     EntityState
    -0.08
    chants
    -0.08
    enler
    -0.08
    è¦
    -0.08
    htag
    -0.08
     Dungeon
    -0.08
    POSITIVE LOGITS
    InThe
    0.10
    opsis
    0.08
    ï
    0.08
     !:
    0.08
    this
    0.08
     cigaret
    0.08
    onet
    0.08
    =$('#
    0.07
     Leonard
    0.07
    (::
    0.07
    Activations Density 0.062%

    No Known Activations