© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 20731
    Prev
    Next
    INDEX
    Explanations

    development

    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
     wives
    -0.06
    .serial
    -0.06
    Bir
    -0.06
     hmac
    -0.06
     opciones
    -0.06
    LP
    -0.06
     отп
    -0.06
     ihr
    -0.06
     bathrooms
    -0.06
    Bin
    -0.06
    POSITIVE LOGITS
     Development
    0.08
     development
    0.07
    AGEMENT
    0.07
     Planning
    0.07
    PMENT
    0.07
    /D
    0.07
     Published
    0.07
    .SH
    0.07
     prosperous
    0.07
     Regulatory
    0.07
    Activations Density 0.020%

    No Known Activations