© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 18139
    Prev
    Next
    INDEX
    Explanations

    this

    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
     lesions
    -0.06
    aset
    -0.06
    alley
    -0.06
     set
    -0.06
    ันว
    -0.06
     UUID
    -0.06
    Set
    -0.06
    anton
    -0.06
    ')[
    -0.06
    .telegram
    -0.06
    POSITIVE LOGITS
     Mirror
    0.07
    .jsx
    0.07
    .xrLabel
    0.06
    -primary
    0.06
    для
    0.06
     для
    0.06
    ivic
    0.06
    تی
    0.06
    保持
    0.06
    Something
    0.06
    Activations Density 0.001%

    No Known Activations