© 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. 124487
    Prev
    Next
    INDEX
    Explanations

    Punctuation and common words

    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
     Controllers
    -0.06
     respect
    -0.06
     себе
    -0.06
     والتي
    -0.06
    赏
    -0.06
    ादन
    -0.06
     фран
    -0.06
    *******************************************************************************/↵
    -0.06
    реп
    -0.06
    министра
    -0.06
    POSITIVE LOGITS
    看见
    0.07
    (period
    0.07
     कथ
    0.07
    Lang
    0.07
    最近
    0.07
    686
    0.07
    suspend
    0.06
    PF
    0.06
    TW
    0.06
     sóc
    0.06
    Activations Density 0.000%

    No Known Activations