© 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. 1669
    Prev
    Next
    INDEX
    Explanations

    it is / it contains

    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
    º«
    -0.09
     Nab
    -0.08
    er
    -0.08
    .wp
    -0.08
    >equals
    -0.08
     nab
    -0.08
    rang
    -0.08
    Trivia
    -0.07
     yourselves
    -0.07
     Abilities
    -0.07
    POSITIVE LOGITS
    ivy
    0.11
    .IsAny
    0.10
    unes
    0.10
    iner
    0.10
     It
    0.09
    amar
    0.09
    ektor
    0.08
    atego
    0.08
     important
    0.08
    inesis
    0.08
    Activations Density 0.024%

    No Known Activations