© 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. 65654
    Prev
    Next
    INDEX
    Explanations

    Crack

    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
    　　　　 　 　
    -0.07
     Appeals
    -0.07
    erspective
    -0.06
    　　　 　 　
    -0.06
    няется
    -0.06
    peated
    -0.06
    Named
    -0.06
    WB
    -0.06
    Authorities
    -0.06
    dom
    -0.06
    POSITIVE LOGITS
     Declarations
    0.07
     هنگام
    0.07
    /documentation
    0.07
     Releases
    0.06
    spec
    0.06
    ประ
    0.06
    اطق
    0.06
    ify
    0.06
     uvol
    0.06
     Vanguard
    0.06
    Activations Density 0.003%

    No Known Activations