© 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. 7-RESID-POST-AA
    6. 24590
    Prev
    Next
    INDEX
    Explanations

    advocate

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trùng
    -0.07
     gir
    -0.07
     crises
    -0.07
     flashes
    -0.07
     �
    -0.07
     순
    -0.07
     Irr
    -0.07
     returns
    -0.07
     Pes
    -0.07
     Slee
    -0.07
    POSITIVE LOGITS
     advocating
    0.14
     advocate
    0.14
     advocates
    0.14
     Advocate
    0.13
     advocated
    0.12
     Advoc
    0.12
     advocacy
    0.12
     advoc
    0.11
    вок
    0.08
     Much
    0.07
    Activations Density 0.003%

    No Known Activations