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. 44819
    Prev
    Next
    INDEX
    Explanations

    investments amount or extent

    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
     LSB
    -0.09
    044
    -0.08
    /cal
    -0.08
    ýt
    -0.08
    ujet
    -0.08
    idth
    -0.08
    PRESS
    -0.08
    noinspection
    -0.08
    GORITH
    -0.08
     contrary
    -0.08
    POSITIVE LOGITS
     mẽ
    0.14
    -duty
    0.13
     into
    0.12
    weights
    0.12
     amounts
    0.12
     vÃło
    0.12
     invest
    0.10
    -weight
    0.10
     towards
    0.10
    -handed
    0.09
    Activations Density 0.005%

    No Known Activations