© 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. 104557
    Prev
    Next
    INDEX
    Explanations

    stop words

    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
    [to
    -0.07
     Shak
    -0.06
    忘
    -0.06
     Ramos
    -0.06
    )<
    -0.06
    λλα
    -0.05
     Figures
    -0.05
    óm
    -0.05
    .toast
    -0.05
    .Height
    -0.05
    POSITIVE LOGITS
    ほ
    0.07
    responses
    0.06
    (boost
    0.06
     جی
    0.06
    锦
    0.06
     getResource
    0.06
    (compact
    0.06
    .CompareTo
    0.06
     kötü
    0.06
     rej
    0.06
    Activations Density 0.029%

    No Known Activations