© 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. 12060
    Prev
    Next
    INDEX
    Explanations

    create immersive virtual reality

    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
     concent
    -0.09
     út
    -0.08
    /Typography
    -0.08
     пн
    -0.08
    uchi
    -0.08
     brom
    -0.08
     ï¼ı:
    -0.08
    .clips
    -0.08
    .SEVER
    -0.08
    _visible
    -0.08
    POSITIVE LOGITS
     virtual
    0.43
     VR
    0.42
     Virtual
    0.38
    VR
    0.38
    Virtual
    0.34
    virtual
    0.33
     vr
    0.32
    èĻļ
    0.31
     Reality
    0.30
     reality
    0.29
    Activations Density 0.133%

    No Known Activations