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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 65383
    Prev
    Next
    INDEX
    Explanations

    quality control and assurance

    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
    ico
    -0.10
    maal
    -0.10
    oning
    -0.09
    CEF
    -0.09
    ndef
    -0.08
    ilm
    -0.08
    arus
    -0.08
    estro
    -0.08
    dain
    -0.08
    /inet
    -0.08
    POSITIVE LOGITS
     measures
    0.16
    led
    0.16
     Freak
    0.14
    æİªæĸ½
    0.13
     processes
    0.13
     freak
    0.12
     Measures
    0.11
     measure
    0.11
     checks
    0.11
     bree
    0.11
    Activations Density 0.007%

    No Known Activations