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. 15-RESID-POST-AA
    6. 60923
    Prev
    Next
    INDEX
    Explanations

    Numbers containing 3 and 5

    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
     eight
    -0.09
    responseObject
    -0.08
     Eighth
    -0.08
    ratio
    -0.07
     numero
    -0.07
    6
    -0.07
    162
    -0.07
    12
    -0.07
     decryption
    -0.07
     sixth
    -0.07
    POSITIVE LOGITS
    esk
    0.08
    น
    0.06
    TECTED
    0.06
    养
    0.06
    OpenHelper
    0.06
    ldkf
    0.06
     htmlspecialchars
    0.06
     podnik
    0.06
     GLint
    0.06
     الأد
    0.06
    Activations Density 0.138%

    No Known Activations