© 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. 128230
    Prev
    Next
    INDEX
    Explanations

    negativity

    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
     田
    -0.07
     BMI
    -0.06
    รษฐ
    -0.06
     cliff
    -0.06
    anc
    -0.06
    深
    -0.06
     fur
    -0.06
     Twenty
    -0.06
    087
    -0.06
    Hat
    -0.06
    POSITIVE LOGITS
     　 　 　 　 　 　
    0.06
     菲律宾
    0.06
    /person
    0.06
    .multipart
    0.06
    /config
    0.06
     '''
↵
    0.06
     pancre
    0.06
     }()↵
    0.06
    (point
    0.06
    herence
    0.06
    Activations Density 0.003%

    No Known Activations