© 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. 30211
    Prev
    Next
    INDEX
    Explanations

    Repairing things

    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
     puzzles
    -0.07
    رده
    -0.07
    ena
    -0.07
    ома
    -0.07
    療
    -0.07
    regexp
    -0.06
    onna
    -0.06
    ench
    -0.06
    ZO
    -0.06
    言う
    -0.06
    POSITIVE LOGITS
    _rot
    0.07
     Starbucks
    0.06
    ngine
    0.06
    exels
    0.06
     çıkart
    0.06
    |R
    0.06
     Constructors
    0.06
     ре
    0.06
    	q
    0.05
     altında
    0.05
    Activations Density 0.035%

    No Known Activations