© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 93604
    Prev
    Next
    INDEX
    Explanations

    colon

    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
     dư
    -0.08
     cruc
    -0.07
    ı
    -0.07
    困
    -0.07
    ertura
    -0.07
    webs
    -0.07
    ndl
    -0.06
     RadioButton
    -0.06
     thiết
    -0.06
     mét
    -0.06
    POSITIVE LOGITS
    uating
    0.06
     viable
    0.06
    .source
    0.05
     وغير
    0.05
    (Frame
    0.05
    (outputs
    0.05
     уник
    0.05
    147
    0.05
     отсутств
    0.05
     enjoys
    0.05
    Activations Density 0.020%

    No Known Activations