© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 80290
    Prev
    Next
    INDEX
    Explanations

    floors and ground

    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
    osaurs
    -0.06
    κυ
    -0.06
    ぬ
    -0.06
    fu
    -0.06
    ndo
    -0.06
     emphasizing
    -0.06
    몬
    -0.05
    ِك
    -0.05
    ES
    -0.05
    赵
    -0.05
    POSITIVE LOGITS
     publicKey
    0.07
     üzerine
    0.07
     connectionString
    0.07
    reset
    0.07
    ізнес
    0.07
    <Input
    0.07
     Česká
    0.07
     possibilities
    0.06
    씀
    0.06
    ibilidade
    0.06
    Activations Density 0.063%

    No Known Activations