© 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. 19-RESID-POST-AA
    11. 124505
    Prev
    Next
    INDEX
    Explanations

    ably

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lecture
    -0.07
    根本
    -0.07
    BJ
    -0.07
    @section
    -0.06
     migrationBuilder
    -0.06
    یط
    -0.06
     яку
    -0.06
     décor
    -0.06
     enquanto
    -0.06
     troublesome
    -0.06
    POSITIVE LOGITS
    brew
    0.07
    POWER
    0.07
    duino
    0.06
     thrift
    0.06
     Cutter
    0.06
    ='%
    0.06
    _proba
    0.06
     проб
    0.06
     Whisper
    0.06
    ="%
    0.06
    Activations Density 0.003%

    No Known Activations