© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 14496
    Prev
    Next
    INDEX
    Explanations

    fuel level, fuel-efficient, fuel source

    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
    tery
    -0.11
    ials
    -0.10
    dia
    -0.10
    ÌĨ
    -0.10
     fat
    -0.10
    appa
    -0.09
    fixtures
    -0.09
    Dia
    -0.09
    lac
    -0.09
    ï¾ij
    -0.09
    POSITIVE LOGITS
    led
    0.30
    ing
    0.26
    er
    0.15
    -efficient
    0.13
    icious
    0.13
    ING
    0.13
    erman
    0.13
    çĥ§
    0.12
    ture
    0.12
    LED
    0.12
    Activations Density 0.023%

    No Known Activations