© 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. 128204
    Prev
    Next
    INDEX
    Explanations

    ato

    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
    11
    -0.07
     asymmetric
    -0.07
     Noble
    -0.07
    ooke
    -0.06
     novelist
    -0.06
     noble
    -0.06
     رایگان
    -0.06
     đời
    -0.06
     sonunda
    -0.06
     Roh
    -0.06
    POSITIVE LOGITS
    ato
    0.12
    ats
    0.12
    AT
    0.11
    Mat
    0.10
    ath
    0.10
    at
    0.10
    ат
    0.10
    aton
    0.10
    atu
    0.10
    atin
    0.10
    Activations Density 0.249%

    No Known Activations