© 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. 44433
    Prev
    Next
    INDEX
    Explanations

    mathematical results and sums

    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
     rest
    -0.12
     remainder
    -0.11
     Duy
    -0.10
     remaining
    -0.10
     zeroes
    -0.10
    ahoo
    -0.10
     Fraction
    -0.09
     multiplying
    -0.09
     Numeric
    -0.09
     multiplication
    -0.09
    POSITIVE LOGITS
     prime
    0.21
     Prime
    0.19
    Prime
    0.16
    prime
    0.15
     tens
    0.13
    _prime
    0.13
     digit
    0.12
     Lucky
    0.12
     odd
    0.12
     sum
    0.12
    Activations Density 0.240%

    No Known Activations