© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 29720
    Prev
    Next
    INDEX
    Explanations

    NSMutable

    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
     çevre
    -0.07
    Associated
    -0.06
     Lý
    -0.06
     Apex
    -0.06
     якого
    -0.06
    .week
    -0.06
     Dios
    -0.06
     ω
    -0.06
     coc
    -0.06
     compens
    -0.06
    POSITIVE LOGITS
     {{--<
    0.07
    لط
    0.07
    pole
    0.07
    něm
    0.07
     invitation
    0.07
     unavailable
    0.07
     NSMutableArray
    0.07
    .mutable
    0.07
    .databind
    0.07
                                                                            
    0.07
    Activations Density 0.001%

    No Known Activations