Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 11-RESID-POST-AA
    6. 123194
    Prev
    Next
    INDEX
    Explanations

    garage

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vouchers
    -0.07
     Cush
    -0.07
     Y
    -0.06
     favourite
    -0.06
    Recognizer
    -0.06
     Floor
    -0.06
     callbacks
    -0.06
     cloth
    -0.06
    -city
    -0.06
     Tick
    -0.06
    POSITIVE LOGITS
     barn
    0.08
     garage
    0.07
     Garage
    0.07
    .groupBox
    0.07
    genre
    0.07
     Institut
    0.07
    #"
    0.07
    EX
    0.06
    _RS
    0.06
     agility
    0.06
    Activations Density 0.004%

    No Known Activations