© 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. 77726
    Prev
    Next
    INDEX
    Explanations

    Citations

    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
    rado
    -0.07
     beef
    -0.07
     densely
    -0.06
     nackt
    -0.06
    _ComCallableWrapper
    -0.06
    хо
    -0.06
    Lean
    -0.06
     مکان
    -0.06
    .NewReader
    -0.06
     왜
    -0.06
    POSITIVE LOGITS
    種
    0.08
    魔法
    0.08
     Ã
    0.07
     홈
    0.06
    航
    0.06
     método
    0.06
    inv
    0.06
     installing
    0.06
     invaluable
    0.06
     employing
    0.06
    Activations Density 0.004%

    No Known Activations