© 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. 44755
    Prev
    Next
    INDEX
    Explanations

    and

    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
     Đề
    -0.07
    Transaction
    -0.06
     prest
    -0.06
     administrators
    -0.06
    Dest
    -0.06
     ladder
    -0.06
     COL
    -0.06
     krát
    -0.06
    Pre
    -0.06
     Indonesia
    -0.06
    POSITIVE LOGITS
     cripp
    0.07
    inged
    0.07
    og
    0.06
    waters
    0.06
    -launch
    0.06
    teborg
    0.06
    AJ
    0.06
    werk
    0.06
     Edison
    0.06
     presumed
    0.06
    Activations Density 0.262%

    No Known Activations