© 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. 15-RESID-POST-AA
    11. 103500
    Prev
    Next
    INDEX
    Explanations

    final

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    posting
    -0.09
     torment
    -0.06
     Bryant
    -0.06
    Mac
    -0.06
    _NEW
    -0.06
     가능
    -0.06
    仙
    -0.06
     autobi
    -0.06
    roof
    -0.06
    setMax
    -0.05
    POSITIVE LOGITS
     SqlCommand
    0.08
     якщо
    0.08
     offense
    0.08
     Unknown
    0.07
    отор
    0.07
     عدم
    0.07
     nevertheless
    0.07
     nej
    0.07
    .drawImage
    0.07
    SEO
    0.07
    Activations Density 0.017%

    No Known Activations