© 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. 57052
    Prev
    Next
    INDEX
    Explanations

    description suffixes

    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
    gamber
    -0.13
    ollectors
    -0.13
    pecific
    -0.12
    groupon
    -0.11
    ernetes
    -0.11
    ÅĽmy
    -0.11
    overy
    -0.11
    racat
    -0.11
    cape
    -0.11
    âĢĮاÛĮ
    -0.11
    POSITIVE LOGITS
    ic
    0.21
    ous
    0.21
    ation
    0.21
    al
    0.21
    ment
    0.20
    ian
    0.20
    ant
    0.19
    ï¸ı
    0.19
    ar
    0.19
    ance
    0.19
    Activations Density 0.391%

    No Known Activations