© 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. 24565
    Prev
    Next
    INDEX
    Explanations

    code snippets/fragments

    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
    Bring
    -0.07
    prec
    -0.07
    prior
    -0.06
     Shine
    -0.06
    (xpath
    -0.06
    Nick
    -0.06
    Interior
    -0.06
    quet
    -0.06
    plor
    -0.06
    .field
    -0.06
    POSITIVE LOGITS
     pneumonia
    0.06
    ":[{↵
    0.06
     economics
    0.06
     inconsistency
    0.06
    monary
    0.06
    ไฟ
    0.06
     personn
    0.06
    /business
    0.06
    .Power
    0.06
    -after
    0.06
    Activations Density 0.000%

    No Known Activations