© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 9615
    Prev
    Next
    INDEX
    Explanations

    places, especially Europe

    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
    ิจ
    -0.07
     Bene
    -0.07
    гот
    -0.07
    datatable
    -0.06
    변
    -0.06
    vest
    -0.06
     Lange
    -0.06
    DON
    -0.06
     Cro
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     наче
    0.06
    薬
    0.06
     laughing
    0.06
     MOUSE
    0.06
    _delegate
    0.06
     준
    0.06
     scrolls
    0.06
     sender
    0.06
    _specs
    0.06
     licens
    0.06
    Activations Density 0.371%

    No Known Activations