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. 20446
    Prev
    Next
    INDEX
    Explanations

    blog posts or news

    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
     insurer
    -0.07
    تباط
    -0.06
     其
    -0.06
     roots
    -0.06
    Multiply
    -0.06
    φορά
    -0.06
    ��
    -0.06
     defenses
    -0.06
     membrane
    -0.06
     Env
    -0.06
    POSITIVE LOGITS
    .dm
    0.06
    .plist
    0.06
    /'↵↵
    0.06
     нож
    0.06
    ":""
    0.06
    ("----------------
    0.06
    ...");↵
    0.06
    assignment
    0.06
    inged
    0.06
     durumunda
    0.06
    Activations Density 0.348%

    No Known Activations