© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 27518
    Prev
    Next
    INDEX
    Explanations

    diagrams

    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
    /N
    -0.07
    PropTypes
    -0.07
    =title
    -0.07
     basePath
    -0.06
     外部リンク
    -0.06
     Zo
    -0.06
    -addons
    -0.06
    cepts
    -0.06
    Th
    -0.06
    يات
    -0.06
    POSITIVE LOGITS
    μβ
    0.07
    اسية
    0.06
    amed
    0.06
    akter
    0.06
    ilight
    0.06
    менту
    0.06
    (DEBUG
    0.06
    денти
    0.06
    ená
    0.06
     místní
    0.06
    Activations Density 0.010%

    No Known Activations