© 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
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 44272
    Prev
    Next
    INDEX
    Explanations

    how-to, howitzer, howled, howstuffworks

    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
     sophistic
    -0.10
    IIIK
    -0.09
    erb
    -0.09
    urette
    -0.09
    nova
    -0.08
    à¸ģำล
    -0.08
    ples
    -0.08
    holm
    -0.08
    /lg
    -0.08
     undef
    -0.08
    POSITIVE LOGITS
    itzer
    0.24
    beit
    0.22
    dy
    0.21
    soever
    0.19
    ards
    0.18
    ling
    0.18
    itz
    0.17
    ls
    0.15
    ie
    0.15
    DY
    0.14
    Activations Density 0.065%

    No Known Activations