© 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. 86398
    Prev
    Next
    INDEX
    Explanations

    research contexts

    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
     histó
    -0.07
    prak
    -0.06
     prior
    -0.06
    .Unity
    -0.06
    Prior
    -0.06
     Prior
    -0.06
    var
    -0.06
     subclass
    -0.06
    竜
    -0.06
    currently
    -0.06
    POSITIVE LOGITS
     nasıl
    0.07
    lients
    0.07
    TestCase
    0.07
    .EMAIL
    0.06
     multiplayer
    0.06
    _DECLS
    0.06
     USERNAME
    0.06
     ]).
    0.06
    adier
    0.06
    _CONV
    0.06
    Activations Density 0.104%

    No Known Activations