© 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 (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 32570
    Prev
    Next
    INDEX
    Explanations

    wind

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ď
    -0.06
    	        	
    -0.06
     Españ
    -0.06
    ����
    -0.06
        
    -0.06
    (history
    -0.06
    ח
    -0.06
    _song
    -0.06
    stakes
    -0.06
         
    -0.06
    POSITIVE LOGITS
     wind
    0.08
    	us
    0.07
    ,v
    0.07
     toJSON
    0.07
    )./
    0.06
     formation
    0.06
    ้าหน
    0.06
     ){
    0.06
     xmin
    0.06
    985
    0.06
    Activations Density 0.003%

    No Known Activations