© 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. 27-RESID-POST-AA
    11. 60328
    Prev
    Next
    INDEX
    Explanations

    queue

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beer
    -0.07
    st
    -0.06
    property
    -0.06
    rails
    -0.06
    .setAction
    -0.06
     Manafort
    -0.06
    t
    -0.06
    *h
    -0.06
     rond
    -0.06
     ornament
    -0.06
    POSITIVE LOGITS
     QUEUE
    0.08
    ufe
    0.08
     messaging
    0.08
     Decomp
    0.07
     queue
    0.07
    :maj
    0.07
    QUEUE
    0.07
     Reactive
    0.07
    ENSE
    0.07
    (keys
    0.07
    Activations Density 0.005%

    No Known Activations