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. 65146
    Prev
    Next
    INDEX
    Explanations

    -ist, -ict, Arist, twist

    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
    er
    -0.20
    rug
    -0.13
    erie
    -0.13
    rin
    -0.12
    erge
    -0.11
    erd
    -0.11
    erp
    -0.11
    erate
    -0.10
    jar
    -0.10
    erer
    -0.10
    POSITIVE LOGITS
    inction
    0.15
    ead
    0.15
    ories
    0.14
    inct
    0.12
    hread
    0.12
    c
    0.12
    ech
    0.12
    ocrats
    0.11
    ries
    0.11
    erna
    0.11
    Activations Density 0.066%

    No Known Activations