© 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. 21267
    Prev
    Next
    INDEX
    Explanations

    but, always, crucial

    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
     persistence
    -0.09
     Persistent
    -0.09
    ULO
    -0.09
    ète
    -0.09
     Persistence
    -0.09
    ç¸
    -0.09
    vana
    -0.08
    ordo
    -0.08
    essenger
    -0.08
    uste
    -0.08
    POSITIVE LOGITS
     always
    0.24
     remained
    0.21
    always
    0.20
     never
    0.20
     remain
    0.20
     siempre
    0.19
     luôn
    0.19
     toujours
    0.19
    Always
    0.19
     sempre
    0.19
    Activations Density 0.038%

    No Known Activations