© 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. 23421
    Prev
    Next
    INDEX
    Explanations

    uncertainty or alternatives

    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
    akis
    -0.09
     Bash
    -0.09
    éĻ¤äºĨ
    -0.09
     obviously
    -0.09
    çī¹åĪ«
    -0.09
     ultimately
    -0.09
    particularly
    -0.09
    oldt
    -0.09
    ARSE
    -0.09
    _firestore
    -0.09
    POSITIVE LOGITS
     instead
    0.20
     perhaps
    0.19
     Instead
    0.18
     maybe
    0.17
     nor
    0.17
     however
    0.17
    Instead
    0.15
     Perhaps
    0.15
     likely
    0.15
     Nor
    0.14
    Activations Density 0.132%

    No Known Activations