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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 36765
    Prev
    Next
    INDEX
    Explanations

    mean

    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
     prohibit
    -0.07
     Fib
    -0.06
     Species
    -0.06
    lh
    -0.06
    istance
    -0.06
    -black
    -0.06
     sleeper
    -0.06
     Visual
    -0.06
     parent
    -0.06
    -event
    -0.06
    POSITIVE LOGITS
    VED
    0.07
     право
    0.07
     ".
    0.07
     '.
    0.07
    言い
    0.06
     sincerely
    0.06
     tinh
    0.06
    aims
    0.06
     bargaining
    0.06
     обычно
    0.06
    Activations Density 0.006%

    No Known Activations