© 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. 4417
    Prev
    Next
    INDEX
    Explanations

    open-mindedness and receptiveness

    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
    856
    -0.10
    олиÑĤ
    -0.10
    Opening
    -0.10
     Mour
    -0.09
    peror
    -0.09
    iosity
    -0.09
    lessness
    -0.09
     Opening
    -0.09
    lobs
    -0.09
    openh
    -0.09
    POSITIVE LOGITS
     mind
    0.13
    -minded
    0.13
     towards
    0.13
    mind
    0.12
    -uri
    0.12
    ess
    0.12
    inded
    0.12
    weathermap
    0.12
     minded
    0.12
     ended
    0.11
    Activations Density 0.008%

    No Known Activations