© 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. 7-RESID-POST-AA
    11. 31091
    Prev
    Next
    INDEX
    Explanations

    Distinctive characteristics

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     saç
    -0.06
     printk
    -0.06
     hygiene
    -0.06
     Budget
    -0.06
     budget
    -0.06
     SVG
    -0.06
    道路
    -0.06
     PhoneNumber
    -0.06
     deviations
    -0.06
    zeros
    -0.06
    POSITIVE LOGITS
    _convert
    0.06
    UniqueId
    0.06
    (isinstance
    0.06
     spacious
    0.06
    ケット
    0.06
     activist
    0.06
    Attempt
    0.06
    .contains
    0.06
    +"/"+
    0.06
     mevcut
    0.06
    Activations Density 0.129%

    No Known Activations