Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 27-RESID-POST-AA
    6. 73175
    Prev
    Next
    INDEX
    Explanations

    migration

    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
     works
    -0.07
     ITEM
    -0.07
    tokens
    -0.07
    (down
    -0.07
     Books
    -0.07
     Booth
    -0.06
    $action
    -0.06
     treasures
    -0.06
     books
    -0.06
     stand
    -0.06
    POSITIVE LOGITS
     migrating
    0.09
     migration
    0.08
    igr
    0.08
     Migration
    0.08
    igrated
    0.07
     pilgrimage
    0.07
     migr
    0.07
     commuter
    0.07
     ominous
    0.07
     migrated
    0.07
    Activations Density 0.009%

    No Known Activations