© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 53925
    Prev
    Next
    INDEX
    Explanations

    Guard

    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
     Title
    -0.08
     tel
    -0.07
    Lee
    -0.07
     真
    -0.07
     peptide
    -0.07
     Lee
    -0.07
    Filename
    -0.07
    Little
    -0.07
     Theme
    -0.07
     Little
    -0.06
    POSITIVE LOGITS
     guard
    0.14
     Guard
    0.14
    guard
    0.13
    -guard
    0.12
     guards
    0.11
     guarding
    0.11
    guards
    0.11
     Guardians
    0.11
    Guard
    0.10
     Guardian
    0.10
    Activations Density 0.009%

    No Known Activations