© 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. 34127
    Prev
    Next
    INDEX
    Explanations

    boat dealership

    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
    IIIK
    -0.11
    ©©
    -0.11
    รà¸ĸ
    -0.11
    trak
    -0.11
    .scalablytyped
    -0.10
    ERRU
    -0.10
    å¾ĴæŃ©
    -0.10
    APTER
    -0.10
    togroup
    -0.09
     tÃłu
    -0.09
    POSITIVE LOGITS
    load
    0.19
    loads
    0.18
     ride
    0.18
    yard
    0.14
    shed
    0.14
    ride
    0.13
    w
    0.13
     driver
    0.13
    ful
    0.12
    -shaped
    0.12
    Activations Density 0.051%

    No Known Activations