© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 61
    Prev
    Next
    INDEX
    Explanations

    the

    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
    Numbers
    -0.06
     Flat
    -0.06
     Hentai
    -0.06
    Index
    -0.06
     Serialization
    -0.06
     komunik
    -0.06
    -definition
    -0.06
    icro
    -0.06
    Issuer
    -0.06
    extensions
    -0.06
    POSITIVE LOGITS
    иж
    0.07
     yarn
    0.07
    เหม
    0.06
    egade
    0.06
    alculate
    0.06
    RIX
    0.06
    аж
    0.06
     аналог
    0.06
    孩
    0.06
     coquine
    0.06
    Activations Density 0.034%

    No Known Activations