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. 14735
    Prev
    Next
    INDEX
    Explanations

    the

    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
     pancakes
    -0.07
     organised
    -0.07
             
    -0.07
    ()))↵↵
    -0.07
    akk
    -0.07
     Ellen
    -0.06
               
    -0.06
    Maria
    -0.06
    رفة
    -0.06
    Das
    -0.06
    POSITIVE LOGITS
    SIG
    0.06
     Ś
    0.05
    shortcut
    0.05
    闲
    0.05
     bied
    0.05
    esper
    0.05
     yı
    0.05
     №
    0.05
    .Documents
    0.05
     сч
    0.05
    Activations Density 0.306%

    No Known Activations