© 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. 58750
    Prev
    Next
    INDEX
    Explanations

    you are tasked or given

    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
    inosaur
    -0.10
    γε
    -0.09
    ç«Ł
    -0.09
    èĩ£
    -0.08
    ARGS
    -0.08
    è§
    -0.08
    ce
    -0.08
    ame
    -0.08
    CanBe
    -0.08
    amak
    -0.08
    POSITIVE LOGITS
     given
    0.18
    given
    0.14
    Given
    0.14
     task
    0.14
     Given
    0.14
     receive
    0.13
    _given
    0.12
    ivent
    0.12
     received
    0.11
     provided
    0.11
    Activations Density 0.170%

    No Known Activations