© 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. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 49597
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Nonnull
    -0.06
    .isChecked
    -0.06
    аря
    -0.06
    чаются
    -0.06
    }-${
    -0.06
    誌
    -0.06
     firepower
    -0.06
    .AllArgsConstructor
    -0.06
    _ctr
    -0.06
     Demon
    -0.06
    POSITIVE LOGITS
     activities
    0.07
     xmlhttp
    0.07
    handle
    0.07
    \Bridge
    0.07
    总
    0.07
    olved
    0.07
     ahead
    0.06
    σπ
    0.06
     appreciated
    0.06
    _Internal
    0.06
    Activations Density 0.014%

    No Known Activations