© 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. 52961
    Prev
    Next
    INDEX
    Explanations

    violations

    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
    _entities
    -0.07
     празд
    -0.07
    .lifecycle
    -0.06
    並
    -0.06
     Art
    -0.06
    	bt
    -0.06
    ’Brien
    -0.06
    .submit
    -0.06
     request
    -0.06
    -before
    -0.06
    POSITIVE LOGITS
    /l
    0.07
    	Image
    0.07
    -K
    0.06
    -delay
    0.06
     Ост
    0.06
    (stat
    0.06
    (game
    0.06
    ously
    0.06
    vy
    0.06
     Prosec
    0.06
    Activations Density 0.036%

    No Known Activations