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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 19-RESID-POST-AA
    6. 91638
    Prev
    Next
    INDEX
    Explanations

    chemical structures

    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
    Face
    -0.07
     fellowship
    -0.06
    ----------------------------------------------------------------------------
    -0.06
     litigation
    -0.06
     embark
    -0.06
    (Field
    -0.06
    757
    -0.06
    GitHub
    -0.06
     Batman
    -0.06
     Ki
    -0.06
    POSITIVE LOGITS
    existent
    0.06
     }];↵
    0.06
    imiento
    0.06
     اصول
    0.06
     пере
    0.06
     privileges
    0.06
    	buttons
    0.06
    .FileWriter
    0.06
    _Send
    0.06
    携
    0.06
    Activations Density 0.031%

    No Known Activations