Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 44891
    Prev
    Next
    INDEX
    Explanations

    numbers and specific nouns

    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
    .
    -0.09
    amu
    -0.09
    :
    -0.08
     Bellev
    -0.08
    .(
    -0.08
     Romero
    -0.08
     +
    -0.08
     Harvey
    -0.08
    cott
    -0.08
    like
    -0.08
    POSITIVE LOGITS
    thew
    0.11
    /Dk
    0.10
    instanc
    0.09
    inh
    0.09
     whom
    0.09
    окÑĥ
    0.08
    (pr
    0.08
    ADDE
    0.08
    agner
    0.08
    PROTO
    0.08
    Activations Density 0.362%

    No Known Activations