© 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. 117195
    Prev
    Next
    INDEX
    Explanations

    period

    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
    .scalablytyped
    -0.06
     外部リンク
    -0.06
     одна
    -0.06
     accountable
    -0.06
     chuẩn
    -0.06
     publicKey
    -0.06
     pointing
    -0.06
     embrace
    -0.06
     scripted
    -0.06
    jekt
    -0.05
    POSITIVE LOGITS
     Transit
    0.06
     transit
    0.06
    Contact
    0.06
    .once
    0.06
     molded
    0.06
     لو
    0.06
     لكل
    0.06
    comm
    0.06
    .then
    0.06
    cial
    0.06
    Activations Density 0.087%

    No Known Activations