© 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. 44487
    Prev
    Next
    INDEX
    Explanations

    also true, important, possible

    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
     conceivable
    -0.12
     doubt
    -0.09
     dubious
    -0.09
    apper
    -0.09
     improbable
    -0.09
     imaginable
    -0.09
     Cair
    -0.09
     ud
    -0.08
    prit
    -0.08
    abar
    -0.08
    POSITIVE LOGITS
     worth
    0.23
     important
    0.19
    worth
    0.18
     Worth
    0.17
     arg
    0.16
     fair
    0.16
     true
    0.15
    important
    0.13
     importante
    0.13
    éĩįè¦ģ
    0.13
    Activations Density 0.038%

    No Known Activations