© 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 (Instruct)
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 94057
    Prev
    Next
    INDEX
    Explanations

    embedded

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Services
    -0.07
     wan
    -0.06
     racism
    -0.06
    /name
    -0.06
     Köy
    -0.06
     Dover
    -0.06
    仓
    -0.06
    perator
    -0.06
     forgot
    -0.05
    Man
    -0.05
    POSITIVE LOGITS
     embedded
    0.15
     Embedded
    0.15
    Embedded
    0.12
    embedded
    0.11
    Av
    0.07
    土
    0.07
    _desc
    0.07
    suppress
    0.07
    .deleteById
    0.07
     возраст
    0.07
    Activations Density 0.004%

    No Known Activations