© 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. 3-RESID-POST-AA
    11. 121328
    Prev
    Next
    INDEX
    Explanations

    custom

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lead
    -0.07
     reven
    -0.07
     reps
    -0.07
    転
    -0.07
    Come
    -0.06
    _ROUTE
    -0.06
    elic
    -0.06
    _if
    -0.06
    과정
    -0.06
     Players
    -0.06
    POSITIVE LOGITS
     custom
    0.13
    custom
    0.12
     customize
    0.10
    -custom
    0.10
    (custom
    0.10
    Custom
    0.09
     accustomed
    0.09
     customization
    0.09
     Custom
    0.09
     CUSTOM
    0.08
    Activations Density 0.013%

    No Known Activations