© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 92924
    Prev
    Next
    INDEX
    Explanations

    recognized

    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
    brook
    -0.07
    ALLED
    -0.06
     Mar
    -0.06
     factors
    -0.06
    OTH
    -0.06
    acha
    -0.06
     decals
    -0.06
    انية
    -0.06
     back
    -0.06
     finish
    -0.06
    POSITIVE LOGITS
                        
↵
    0.06
     woes
    0.06
    	Json
    0.06
    是一个
    0.06
    -capital
    0.06
    express
    0.06
     」
    0.06
     встре
    0.06
     forc
    0.06
    ��
    0.06
    Activations Density 0.018%

    No Known Activations