© 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. 35714
    Prev
    Next
    INDEX
    Explanations

    to

    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
    plaintext
    -0.06
    wendung
    -0.06
    /run
    -0.06
    POSITORY
    -0.06
    んです
    -0.06
     cairo
    -0.06
    nowledge
    -0.06
    Slf
    -0.06
     öl
    -0.06
     scant
    -0.06
    POSITIVE LOGITS
     pesso
    0.07
    DED
    0.06
    蔵
    0.06
    ово
    0.06
    作为
    0.06
    SUR
    0.06
    雙
    0.06
    (timer
    0.06
     consistently
    0.06
    ，为
    0.06
    Activations Density 0.028%

    No Known Activations