© 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 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. 15-RESID-POST-AA
    11. 26306
    Prev
    Next
    INDEX
    Explanations

    abuse/assault timing

    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
    團
    -0.07
    ัคร
    -0.07
    ğü
    -0.07
    .master
    -0.07
     Diese
    -0.06
     bü
    -0.06
     tracked
    -0.06
     obstacle
    -0.06
     prominently
    -0.06
    泊
    -0.06
    POSITIVE LOGITS
    ANJI
    0.06
     держав
    0.06
    ificador
    0.06
     ช
    0.06
    /apis
    0.06
    Associated
    0.06
    طال
    0.06
    가격
    0.06
    /GL
    0.06
    /remove
    0.06
    Activations Density 0.013%

    No Known Activations