© 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
    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. 39877
    Prev
    Next
    INDEX
    Explanations

    class

    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
    _RAW
    -0.07
     nuit
    -0.07
    річ
    -0.06
     menacing
    -0.06
     warehouses
    -0.06
    연구
    -0.06
     февра
    -0.06
     harassment
    -0.06
     homage
    -0.06
    InOut
    -0.06
    POSITIVE LOGITS
    -Class
    0.07
     improving
    0.07
     requiring
    0.06
    decoded
    0.06
    _beg
    0.06
     Interface
    0.06
     antiqu
    0.06
     paragraph
    0.06
     Employ
    0.06
    	td
    0.06
    Activations Density 0.007%

    No Known Activations