© 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. 27662
    Prev
    Next
    INDEX
    Explanations

    ang

    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
    аче
    -0.08
     daemon
    -0.07
    ISTORY
    -0.07
    Price
    -0.07
    ()).
    -0.07
    �示
    -0.07
    .fecha
    -0.07
     politics
    -0.07
    forth
    -0.07
    .YES
    -0.07
    POSITIVE LOGITS
     Eston
    0.06
    ěn
    0.06
     dangling
    0.06
     ­
    0.06
     getInstance
    0.05
     zeměděl
    0.05
     Seq
    0.05
     ApplicationException
    0.05
    [String
    0.05
    =text
    0.05
    Activations Density 0.001%

    No Known Activations