© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 25831
    Prev
    Next
    INDEX
    Explanations

    async

    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
    Membership
    -0.07
    _wallet
    -0.07
    step
    -0.07
    grav
    -0.07
     dobře
    -0.07
    _d
    -0.07
    ,P
    -0.06
     precipitation
    -0.06
    .nil
    -0.06
    Jessica
    -0.06
    POSITIVE LOGITS
    _preview
    0.07
     offensive
    0.07
    altern
    0.06
     pertinent
    0.06
     buyer
    0.06
    sequential
    0.06
     TRY
    0.06
    Async
    0.06
     žal
    0.06
     gfx
    0.06
    Activations Density 0.001%

    No Known Activations