© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 45138
    Prev
    Next
    INDEX
    Explanations

    abbreviations and initialisms

    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
    ìĶ©
    -0.10
    ãģĬãĤĬ
    -0.10
    echa
    -0.09
    agara
    -0.09
    ished
    -0.09
    etta
    -0.09
    itsu
    -0.09
     dispose
    -0.09
     concession
    -0.09
    zet
    -0.09
    POSITIVE LOGITS
    ftware
    0.13
     eÄŁer
    0.10
    vere
    0.10
    tlement
    0.10
    à¥Ģमत
    0.10
    atchewan
    0.10
    vent
    0.10
    opolitan
    0.09
    iling
    0.09
    emean
    0.09
    Activations Density 0.354%

    No Known Activations