Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 45000
    Prev
    Next
    INDEX
    Explanations

    cannot perform action

    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
    unn
    -0.09
     минÑĥ
    -0.09
     casual
    -0.09
     unw
    -0.09
    atu
    -0.09
     seriousness
    -0.09
     dist
    -0.09
     Slee
    -0.09
    éģķ
    -0.09
     monoc
    -0.09
    POSITIVE LOGITS
     inability
    0.15
     unable
    0.15
     Unable
    0.14
     Sorry
    0.13
     sorry
    0.12
    åĿ¦
    0.12
     unknown
    0.12
     admitting
    0.12
     empty
    0.12
     shr
    0.12
    Activations Density 0.155%

    No Known Activations