© 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. 27-RESID-POST-AA
    11. 93972
    Prev
    Next
    INDEX
    Explanations

    medical/anatomical conditions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    44
    -0.07
    塔
    -0.07
     الس
    -0.07
     Setting
    -0.07
    -ed
    -0.06
     �
    -0.06
    841
    -0.06
     fot
    -0.06
    _,,
    -0.06
    سل
    -0.06
    POSITIVE LOGITS
    uluk
    0.08
    (True
    0.07
     commenc
    0.06
    .handlers
    0.06
     readline
    0.06
     sentenced
    0.06
    」「
    0.06
     个
    0.06
    igkeit
    0.06
    った
    0.06
    Activations Density 0.028%

    No Known Activations