© 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. 45172
    Prev
    Next
    INDEX
    Explanations

    General statements/advice

    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
    緊
    -0.06
    ấp
    -0.06
    ImageData
    -0.06
    )<
    -0.06
     cityName
    -0.06
    maxLength
    -0.06
    (ra
    -0.06
    ящих
    -0.06
     vx
    -0.06
    _CH
    -0.06
    POSITIVE LOGITS
    comb
    0.08
    APSHOT
    0.07
    -components
    0.07
     associations
    0.06
    Spider
    0.06
     عليك
    0.06
    YRO
    0.06
    رير
    0.06
    (first
    0.06
    -event
    0.06
    Activations Density 0.269%

    No Known Activations