© 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. 11-RESID-POST-AA
    11. 93753
    Prev
    Next
    INDEX
    Explanations

    emails/letters

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     사회
    -0.06
    _cover
    -0.06
    ument
    -0.06
     sui
    -0.06
    Bạn
    -0.06
    Ljava
    -0.06
     gren
    -0.06
    .Consumer
    -0.06
    $app
    -0.05
     CHUNK
    -0.05
    POSITIVE LOGITS
    呀
    0.07
    ezpe
    0.07
    (\$
    0.07
    уй
    0.07
    startIndex
    0.06
     integrating
    0.06
     Diversity
    0.06
     kromě
    0.06
     invested
    0.06
     probable
    0.06
    Activations Density 0.021%

    No Known Activations