© 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. 11-RESID-POST-AA
    11. 52270
    Prev
    Next
    INDEX
    Explanations

    nowrap

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    getDrawable
    -0.06
     після
    -0.06
     является
    -0.06
    bjerg
    -0.06
     Suk
    -0.06
    tribution
    -0.06
    rics
    -0.06
     punished
    -0.06
    avorites
    -0.06
     شخصية
    -0.06
    POSITIVE LOGITS
    nowrap
    0.08
     nowrap
    0.08
    ogeneity
    0.07
     fastest
    0.07
     straightforward
    0.07
    concert
    0.07
     frankly
    0.07
    Ajax
    0.07
    .crt
    0.07
     throw
    0.06
    Activations Density 0.001%

    No Known Activations