© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 102209
    Prev
    Next
    INDEX
    Explanations

    providing information

    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
     prefer
    -0.08
    ansk
    -0.08
     sinks
    -0.07
     العام
    -0.07
     Wor
    -0.07
     memories
    -0.07
    wake
    -0.07
    Malloc
    -0.07
     apolog
    -0.07
    میر
    -0.07
    POSITIVE LOGITS
     다양한
    0.06
    _UTF
    0.06
    金属
    0.06
     действ
    0.05
    疾
    0.05
    ScreenState
    0.05
    -cat
    0.05
    _links
    0.05
    bate
    0.05
     Northwest
    0.05
    Activations Density 0.035%

    No Known Activations