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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 15-RESID-POST-AA
    6. 111100
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     associates
    -0.06
     bigger
    -0.06
    Dynamic
    -0.06
    alpha
    -0.06
    _relationship
    -0.06
     السلام
    -0.06
     Sister
    -0.05
    ३
    -0.05
     attendee
    -0.05
    _catalog
    -0.05
    POSITIVE LOGITS
    .states
    0.08
    frau
    0.08
     waypoints
    0.07
    zeigt
    0.07
     особенно
    0.07
     تعداد
    0.06
    мів
    0.06
     teal
    0.06
    	rv
    0.06
    .buttons
    0.06
    Activations Density 0.008%

    No Known Activations