© 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. 49989
    Prev
    Next
    INDEX
    Explanations

    :

    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
    -0.06
    fir
    -0.06
    ı
    -0.06
     Fac
    -0.06
    ुक
    -0.06
     carg
    -0.06
    ukarı
    -0.06
    grunt
    -0.06
     accreditation
    -0.06
     onPause
    -0.06
    POSITIVE LOGITS
    (Object
    0.07
     intervening
    0.07
     پس
    0.07
     Dragons
    0.07
     Raised
    0.06
     Unified
    0.06
    ;"↵
    0.06
     Auto
    0.06
    Geometry
    0.06
    icians
    0.06
    Activations Density 0.001%

    No Known Activations