© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 127383
    Prev
    Next
    INDEX
    Explanations

    for

    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
    Not in Any Lists

    No Comments

    Negative Logits
    .driver
    -0.09
     safety
    -0.07
    _ly
    -0.07
     to
    -0.07
    .bc
    -0.07
    _cluster
    -0.07
     steep
    -0.07
    ادية
    -0.06
     Dynasty
    -0.06
    >
    -0.06
    POSITIVE LOGITS
     utilisateur
    0.07
     challenger
    0.06
     sürekli
    0.06
     Melbourne
    0.06
    ORTH
    0.06
    itled
    0.05
     Verd
    0.05
     örnek
    0.05
     elabor
    0.05
    Foto
    0.05
    Activations Density 0.026%

    No Known Activations