© 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. 26037
    Prev
    Next
    INDEX
    Explanations

    uc

    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
    พาะ
    -0.07
     felse
    -0.06
    ییر
    -0.06
     battlefield
    -0.06
    ertime
    -0.06
     tragedy
    -0.06
     Oscar
    -0.06
     farm
    -0.06
     CITY
    -0.06
     trending
    -0.06
    POSITIVE LOGITS
    u
    0.12
    ul
    0.11
    ub
    0.11
    um
    0.11
    ut
    0.10
    un
    0.10
    ur
    0.10
    ua
    0.10
     Mu
    0.10
    cura
    0.10
    Activations Density 1.768%

    No Known Activations