© 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. 11-RESID-POST-AA
    11. 47693
    Prev
    Next
    INDEX
    Explanations

    amplitude

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "As
    -0.07
     succession
    -0.07
     turning
    -0.07
    .i
    -0.07
     timeless
    -0.07
    conf
    -0.07
    .to
    -0.06
     oss
    -0.06
     Info
    -0.06
    esco
    -0.06
    POSITIVE LOGITS
     amplitude
    0.14
    plitude
    0.09
    رانه
    0.07
    -plane
    0.07
    clamp
    0.06
    une
    0.06
    mute
    0.06
     vog
    0.06
    'name
    0.06
     plane
    0.06
    Activations Density 0.008%

    No Known Activations