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. 15-RESID-POST-AA
    6. 120402
    Prev
    Next
    INDEX
    Explanations

    ">"

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    وح
    -0.07
    Jesus
    -0.07
    Sir
    -0.07
    Ken
    -0.07
    Bell
    -0.06
    principal
    -0.06
     πάνω
    -0.06
     světě
    -0.06
     gor
    -0.06
     otherwise
    -0.06
    POSITIVE LOGITS
     roleId
    0.07
    (memory
    0.07
    "><!--
    0.07
     sexism
    0.06
        
    ↵    
    ↵
    0.06
            
    ↵        
    ↵
    0.06
     STDMETHOD
    0.06
    dato
    0.06
     جامعه
    0.06
     Minimum
    0.06
    Activations Density 0.002%

    No Known Activations