© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 33998
    Prev
    Next
    INDEX
    Explanations

    situations or conditions

    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
     Cove
    -0.10
    axy
    -0.09
    .executeQuery
    -0.09
    adem
    -0.09
    xia
    -0.09
    oref
    -0.09
    OVE
    -0.08
    oval
    -0.08
    mani
    -0.08
    ä½ĵç³»
    -0.08
    POSITIVE LOGITS
     exact
    0.16
     there
    0.15
    ver
    0.15
     stakes
    0.12
     speed
    0.12
     utmost
    0.12
     absolute
    0.11
     quick
    0.11
     little
    0.11
     it
    0.10
    Activations Density 0.043%

    No Known Activations