© 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. 79885
    Prev
    Next
    INDEX
    Explanations

    are

    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
    şehir
    -0.07
    zenie
    -0.07
    bao
    -0.07
    Edit
    -0.07
     Flynn
    -0.07
     booth
    -0.06
     št
    -0.06
     Halloween
    -0.06
    blk
    -0.06
    (z
    -0.06
    POSITIVE LOGITS
    .network
    0.07
     ag
    0.07
     instit
    0.06
    DEPEND
    0.06
     factory
    0.06
    латы
    0.06
    之间
    0.06
     fertil
    0.06
    )new
    0.06
    hod
    0.06
    Activations Density 0.006%

    No Known Activations