© 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. 38622
    Prev
    Next
    INDEX
    Explanations

    provide information and answer

    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
     primaries
    -0.10
     Vul
    -0.10
    âĪ§
    -0.09
    pher
    -0.09
     Actual
    -0.09
    ãģ«ãģ¤
    -0.08
    971
    -0.08
    actual
    -0.08
    essler
    -0.08
    .rs
    -0.08
    POSITIVE LOGITS
     general
    0.18
     plenty
    0.14
     information
    0.13
    general
    0.13
     if
    0.12
     generic
    0.11
     response
    0.11
     général
    0.11
     some
    0.11
     answer
    0.11
    Activations Density 0.143%

    No Known Activations