© 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. 13205
    Prev
    Next
    INDEX
    Explanations

    preposition "in" followed by locations or events

    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
     anticipation
    -0.14
     tandem
    -0.12
     defiance
    -0.10
     anticipating
    -0.10
    utos
    -0.09
     eve
    -0.09
     Mechanics
    -0.09
     Grocery
    -0.08
     TERMS
    -0.08
    å¤ĩ
    -0.08
    POSITIVE LOGITS
     exchange
    0.14
     absent
    0.13
     dro
    0.12
     response
    0.11
    uffs
    0.11
     circumstances
    0.10
    exchange
    0.10
     secret
    0.10
     hopes
    0.10
    achi
    0.10
    Activations Density 0.119%

    No Known Activations