© 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
    5. 50-RESID-POST-GF
    7. 37969
    Prev
    Next
    INDEX
    Explanations

    many possibilities

    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
    üzel
    -0.09
    insky
    -0.08
    AVA
    -0.08
    zel
    -0.08
     three
    -0.08
    abus
    -0.08
    以ä¸ĭ
    -0.08
    zier
    -0.08
    .inc
    -0.08
    rer
    -0.08
    POSITIVE LOGITS
     many
    0.21
    many
    0.17
     MANY
    0.16
     Many
    0.15
    Many
    0.14
    -many
    0.14
     possible
    0.14
     possibilities
    0.13
     available
    0.13
     muit
    0.13
    Activations Density 0.016%

    No Known Activations