© 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 (Instruct)
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 73468
    Prev
    Next
    INDEX
    Explanations

    100

    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
    Fort
    -0.07
    Face
    -0.07
     Rivers
    -0.07
    Sol
    -0.07
     speaking
    -0.07
    NSDictionary
    -0.07
     Relative
    -0.07
     Surface
    -0.06
     measurable
    -0.06
     останов
    -0.06
    POSITIVE LOGITS
    猛
    0.06
    alli
    0.06
     MUT
    0.06
    を行
    0.06
     فتح
    0.06
    'gc
    0.06
     sleek
    0.06
    brands
    0.06
     köy
    0.06
     parentNode
    0.06
    Activations Density 0.006%

    No Known Activations