© 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. 15-RESID-POST-AA
    11. 100434
    Prev
    Next
    INDEX
    Explanations

    research studies

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    trigger
    -0.07
    Han
    -0.06
    (match
    -0.06
    -Disposition
    -0.06
    _patient
    -0.06
     夏
    -0.06
    #",
    -0.06
     Figure
    -0.06
    (col
    -0.06
    (actor
    -0.06
    POSITIVE LOGITS
     AlertDialog
    0.08
    .Throw
    0.07
    NDAR
    0.06
    ває
    0.06
     overdose
    0.06
     generate
    0.06
     Huyện
    0.06
    rvé
    0.06
    IgnoreCase
    0.06
    aje
    0.06
    Activations Density 0.043%

    No Known Activations