Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 81107
    Prev
    Next
    INDEX
    Explanations

    articles

    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
    燕
    -0.07
    .getElements
    -0.07
     Дж
    -0.07
    -is
    -0.07
    stderr
    -0.06
     tabIndex
    -0.06
     polis
    -0.06
     Hakk
    -0.06
    니아
    -0.06
    .setFocus
    -0.06
    POSITIVE LOGITS
     prá
    0.06
     треть
    0.06
     doorway
    0.06
     Condition
    0.06
     �
    0.06
     surprises
    0.06
     irrelevant
    0.06
    戰
    0.06
    GM
    0.06
     dairy
    0.06
    Activations Density 0.104%

    No Known Activations