Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 50403
    Prev
    Next
    INDEX
    Explanations

    directory paths

    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
     �
    -0.07
     mcc
    -0.07
     系
    -0.06
     misinformation
    -0.06
     微
    -0.06
    елем
    -0.06
     ={
    -0.06
     využití
    -0.06
    lies
    -0.06
     ";"
    -0.06
    POSITIVE LOGITS
    	    		
    0.07
    			    
    0.07
     روح
    0.07
    			
    0.07
     \<
    0.06
    ilitary
    0.06
     capacit
    0.06
    	match
    0.06
    				
    0.06
    _physical
    0.06
    Activations Density 0.001%

    No Known Activations