© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 15070
    Prev
    Next
    INDEX
    Explanations

    MC and named characters

    np_acts-logits-general · gemini-2.5-flash-lite

    references to placeholder identifiers and other special/meta tokens (e.g., name slots and formatting markers) rather than ordinary words.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    .MixedReality
    -0.09
     shorthand
    -0.09
    ometr
    -0.09
    ¶Į
    -0.08
    ~-~-~-~-
    -0.08
    ëį°ìĿ´íĬ¸
    -0.08
    combe
    -0.08
    cheid
    -0.08
    703
    -0.08
    eref
    -0.08
    POSITIVE LOGITS
    cis
    0.08
    ï½Ģãĥ½
    0.08
     Ire
    0.08
     impost
    0.07
     today
    0.07
    coding
    0.07
    bal
    0.07
    795
    0.07
     Milo
    0.07
     eiusmod
    0.07
    Activations Density 0.439%

    No Known Activations