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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 19-RESID-POST-AA
    6. 30896
    Prev
    Next
    INDEX
    Explanations

    scientific abstracts

    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
    bling
    -0.06
     stere
    -0.06
     días
    -0.06
     Dee
    -0.06
    クリ
    -0.06
    first
    -0.06
     Phi
    -0.06
    イ
    -0.06
     cuanto
    -0.06
    rhs
    -0.06
    POSITIVE LOGITS
    сутств
    0.06
    ّة
    0.06
    (Register
    0.06
    Pooling
    0.06
     �
    0.06
    .security
    0.06
     تهران
    0.06
     toolbar
    0.06
     표
    0.06
     disposing
    0.06
    Activations Density 0.189%

    No Known Activations