© 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. 129869
    Prev
    Next
    INDEX
    Explanations

    code, informal writing

    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
     regional
    -0.06
    (Service
    -0.06
     �
    -0.06
     cư
    -0.06
     mash
    -0.06
     definition
    -0.06
     sheets
    -0.06
     kur
    -0.06
     bak
    -0.06
    LEX
    -0.06
    POSITIVE LOGITS
    ğen
    0.07
    _optimizer
    0.06
    Soon
    0.06
    ./
    0.06
     ExecutionContext
    0.06
     PIPE
    0.06
     πλη
    0.06
     آثار
    0.06
     Recently
    0.06
     инструмент
    0.06
    Activations Density 0.000%

    No Known Activations