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. 19-RESID-POST-AA
    6. 51500
    Prev
    Next
    INDEX
    Explanations

    re

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     خانم
    -0.06
     grin
    -0.06
    Minimal
    -0.06
     neboť
    -0.06
     Dollar
    -0.06
    Fixture
    -0.06
    deriv
    -0.06
     içine
    -0.06
     bred
    -0.06
     strstr
    -0.06
    POSITIVE LOGITS
    μα
    0.08
    ισ
    0.06
    �
    0.06
    ics
    0.06
    	option
    0.06
     scans
    0.06
    ensions
    0.06
    支
    0.06
    обра�
    0.06
    science
    0.05
    Activations Density 0.004%

    No Known Activations