© 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. 466
    Prev
    Next
    INDEX
    Explanations

    talking with human

    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
    ikel
    -0.09
     fug
    -0.08
    embro
    -0.08
    å°½
    -0.08
    oi
    -0.08
    Reporter
    -0.08
    ontology
    -0.08
    redient
    -0.08
    654
    -0.08
     Hess
    -0.08
    POSITIVE LOGITS
     human
    0.38
     humans
    0.38
    human
    0.28
    人类
    0.27
    -human
    0.27
     ÑĩеловеÑĩеÑģ
    0.25
     Humans
    0.24
     Human
    0.24
    Humans
    0.23
    Human
    0.22
    Activations Density 0.084%

    No Known Activations