© 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. 45428
    Prev
    Next
    INDEX
    Explanations

    from

    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
     Sends
    -0.07
     =>
↵
    -0.07
     र
    -0.07
     Pregn
    -0.07
     DEVICE
    -0.07
    )|
    -0.06
     Recogn
    -0.06
    ...")↵
    -0.06
     XF
    -0.06
     expecting
    -0.06
    POSITIVE LOGITS
     olmadığı
    0.07
    ENA
    0.06
     dipl
    0.06
     appropriation
    0.06
    -axis
    0.06
    _MAKE
    0.06
     sweat
    0.06
     flagship
    0.06
    .gt
    0.06
    VOID
    0.06
    Activations Density 0.000%

    No Known Activations