© 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. 17747
    Prev
    Next
    INDEX
    Explanations

    starts with H words

    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
    ash
    -0.12
    azel
    -0.12
    elpers
    -0.11
    amar
    -0.11
    elp
    -0.11
    arness
    -0.10
    ooks
    -0.10
    older
    -0.10
    ASH
    -0.10
    its
    -0.10
    POSITIVE LOGITS
    264
    0.16
     Bomb
    0.13
    r
    0.13
     bomb
    0.13
     ere
    0.13
    itory
    0.12
    bomb
    0.12
    ella
    0.12
    ight
    0.12
     alf
    0.11
    Activations Density 0.053%

    No Known Activations