© 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. 56723
    Prev
    Next
    INDEX
    Explanations

    scientific/medical studies

    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
     models
    -0.07
     โ
    -0.07
     elo
    -0.06
    dj
    -0.06
     bridal
    -0.06
     duel
    -0.06
     Decision
    -0.06
     Dro
    -0.06
     operate
    -0.06
     quaternion
    -0.06
    POSITIVE LOGITS
    ]));
    0.07
    .clipsToBounds
    0.07
    reste
    0.07
     непосред
    0.07
    bs
    0.06
     ".",
    0.06
    .viewport
    0.06
    __);
    0.06
    .backup
    0.06
    InTheDocument
    0.06
    Activations Density 0.093%

    No Known Activations