© 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. 15-RESID-POST-AA
    11. 32459
    Prev
    Next
    INDEX
    Explanations

    of

    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
    .Do
    -0.07
    ("'",
    -0.07
    되지
    -0.06
    "Yes
    -0.06
    џџџџ
    -0.06
    해보
    -0.06
     fácil
    -0.06
    _Double
    -0.06
    ib
    -0.06
    ド
    -0.06
    POSITIVE LOGITS
     Bounty
    0.07
     relationship
    0.06
     متخصص
    0.06
    "]=$
    0.06
     －
    0.06
     mater
    0.06
     variability
    0.06
     coun
    0.06
    WK
    0.06
    pressive
    0.06
    Activations Density 0.045%

    No Known Activations