Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 93136
    Prev
    Next
    INDEX
    Explanations

    age

    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
    xCD
    -0.07
    centers
    -0.07
    vs
    -0.07
     Hits
    -0.06
    Things
    -0.06
    歩
    -0.06
    OK
    -0.06
    敏
    -0.06
    Muslim
    -0.06
     novels
    -0.06
    POSITIVE LOGITS
    istribution
    0.07
     breast
    0.07
    ence
    0.07
    .place
    0.07
     Af
    0.06
    (deg
    0.06
     posture
    0.06
     temperament
    0.06
    _fe
    0.06
    ereco
    0.06
    Activations Density 0.003%

    No Known Activations