© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 36536
    Prev
    Next
    INDEX
    Explanations

    Mixed-language text

    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
    Negative Logits
    _music
    -0.07
     <<
    -0.07
    属于
    -0.07
     snprintf
    -0.06
     revolt
    -0.06
     objections
    -0.06
    言葉
    -0.06
    iqué
    -0.06
    hunter
    -0.06
     LO
    -0.06
    POSITIVE LOGITS
    idf
    0.06
     обеспе
    0.06
    -directory
    0.06
    -eff
    0.06
     И
    0.06
     któ
    0.06
    .Identifier
    0.06
     بتوان
    0.06
    .Iterator
    0.06
    ff
    0.06
    Activations Density 0.012%

    No Known Activations