© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 9502
    Prev
    Next
    INDEX
    Explanations

    technical descriptions

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يق
    -0.07
     lasted
    -0.06
    iguiente
    -0.06
     Protocol
    -0.06
     سام
    -0.06
    .directive
    -0.06
    ンバ
    -0.06
    imestep
    -0.06
    perature
    -0.06
     Liability
    -0.06
    POSITIVE LOGITS
     VALID
    0.07
    +x
    0.07
     Raise
    0.06
     Spreadsheet
    0.06
    Box
    0.06
     вывод
    0.06
    Missing
    0.06
     Silent
    0.06
     Honest
    0.06
    :red
    0.06
    Activations Density 0.236%

    No Known Activations