© 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. 15-RESID-POST-AA
    11. 24494
    Prev
    Next
    INDEX
    Explanations

    He

    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
    Negative Logits
     after
    -0.07
     unintended
    -0.07
     wallet
    -0.07
     useRef
    -0.07
     spaced
    -0.07
     Experiment
    -0.07
     packet
    -0.06
     proprio
    -0.06
     algo
    -0.06
    야
    -0.06
    POSITIVE LOGITS
    toa
    0.07
    ","\
    0.06
     논
    0.06
     ю
    0.06
    Cell
    0.06
    inston
    0.06
    	buff
    0.06
    .Url
    0.05
    .enemy
    0.05
    _FAR
    0.05
    Activations Density 0.000%

    No Known Activations