© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 14002
    Prev
    Next
    INDEX
    Explanations

    serial contexts

    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
    ãģĬãĤĬ
    -0.12
    ioned
    -0.11
    edii
    -0.10
    fulness
    -0.10
    gend
    -0.09
    orda
    -0.09
     Multiply
    -0.09
    ary
    -0.09
    unts
    -0.09
    óc
    -0.09
    POSITIVE LOGITS
    izable
    0.21
    ly
    0.19
    VersionUID
    0.18
    izing
    0.18
    .Serial
    0.17
    izations
    0.17
    ised
    0.17
    ity
    0.16
    s
    0.16
    izers
    0.16
    Activations Density 0.014%

    No Known Activations