© 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. 38107
    Prev
    Next
    INDEX
    Explanations

    metrics and rates

    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
     prim
    -0.10
     Brut
    -0.10
    ongyang
    -0.09
     Pig
    -0.09
    ongan
    -0.09
    _THRESH
    -0.09
    Abb
    -0.09
    NECT
    -0.09
     str
    -0.09
     Abed
    -0.09
    POSITIVE LOGITS
     number
    0.16
     Mean
    0.12
     Number
    0.12
     average
    0.11
     reduction
    0.11
     measures
    0.11
     Matth
    0.11
     sá»ij
    0.11
    Number
    0.10
     dollars
    0.10
    Activations Density 0.101%

    No Known Activations