© 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. 11-RESID-POST-AA
    11. 93779
    Prev
    Next
    INDEX
    Explanations

    parenthesis

    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
     Eventually
    -0.07
    Food
    -0.07
     myocard
    -0.06
     �
    -0.06
     BRE
    -0.06
     chưa
    -0.06
    試
    -0.06
     çocuk
    -0.06
     modify
    -0.06
    _firestore
    -0.06
    POSITIVE LOGITS
     Subjects
    0.07
    eydi
    0.06
    cycl
    0.06
     Roulette
    0.06
    pipes
    0.06
    -debug
    0.06
    ап
    0.06
    ு
    0.06
    ıkl
    0.06
    lift
    0.06
    Activations Density 0.040%

    No Known Activations