© 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
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 53655
    Prev
    Next
    INDEX
    Explanations

    to

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     범
    -0.07
    uesday
    -0.07
     خدا
    -0.07
    神
    -0.07
     神
    -0.06
     Dios
    -0.06
    EFAULT
    -0.06
    รษฐ
    -0.06
     Mit
    -0.06
    	UI
    -0.06
    POSITIVE LOGITS
     excessive
    0.07
     ود
    0.07
     robust
    0.07
     corrections
    0.07
    -scroll
    0.06
     cohesion
    0.06
     pledged
    0.06
     ft
    0.06
     broken
    0.06
     whilst
    0.06
    Activations Density 0.004%

    No Known Activations