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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3-RESID-POST-AA
    11. 93566
    Prev
    Next
    INDEX
    Explanations

    in

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Бор
    -0.07
    bara
    -0.06
     TM
    -0.06
    ("");↵↵
    -0.06
     потріб
    -0.06
     };↵↵
    -0.06
    !”↵↵
    -0.06
     Druh
    -0.06
    .RESULT
    -0.06
     differentiate
    -0.06
    POSITIVE LOGITS
    _BLK
    0.07
    in
    0.06
    (upload
    0.06
    γο
    0.06
     ocean
    0.06
    IN
    0.06
     FIN
    0.06
     Ethi
    0.06
    .ease
    0.06
    obic
    0.06
    Activations Density 0.109%

    No Known Activations