Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 93878
    Prev
    Next
    INDEX
    Explanations

    Non-English, punctuation

    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
     vlan
    -0.07
     cel
    -0.07
    calar
    -0.06
     cine
    -0.06
    BUTTON
    -0.06
     элем
    -0.06
     трансп
    -0.06
    силь
    -0.06
    以下
    -0.06
     quests
    -0.06
    POSITIVE LOGITS
     전국
    0.07
     Ελλάδα
    0.06
     získ
    0.06
     Retrofit
    0.06
     $$
    0.06
    ểm
    0.06
     Talking
    0.06
    andWhere
    0.06
    Activate
    0.06
     Weiter
    0.06
    Activations Density 0.013%

    No Known Activations