© 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. 11-RESID-POST-AA
    11. 76410
    Prev
    Next
    INDEX
    Explanations

    Sports

    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
    тин
    -0.06
    enne
    -0.06
     wing
    -0.06
     Crus
    -0.06
     melan
    -0.06
     Dahl
    -0.06
     CD
    -0.06
     OK
    -0.06
     llama
    -0.06
     vốn
    -0.06
    POSITIVE LOGITS
    ItemSelectedListener
    0.07
    們
    0.06
    ursed
    0.06
    _INTEGER
    0.06
     ділян
    0.06
    "Our
    0.06
     Files
    0.06
    .redirect
    0.06
     detects
    0.06
    Jennifer
    0.06
    Activations Density 0.028%

    No Known Activations