© 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. 2954
    Prev
    Next
    INDEX
    Explanations

    industries, including

    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
     nomine
    -0.09
    arna
    -0.09
    onis
    -0.09
    tober
    -0.09
    itle
    -0.08
    atk
    -0.08
    EDITOR
    -0.08
    WithTag
    -0.08
     Ziel
    -0.08
    Ľå»º
    -0.08
    POSITIVE LOGITS
     such
    0.17
     sectors
    0.14
     vertical
    0.11
    kv
    0.11
    hores
    0.11
     likes
    0.10
    bens
    0.10
     segments
    0.10
    pecific
    0.10
     including
    0.10
    Activations Density 0.016%

    No Known Activations