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. 53598
    Prev
    Next
    INDEX
    Explanations

    OpenCV matrix datatype

    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
    íky
    -0.07
    Poss
    -0.07
    囲
    -0.06
     Penis
    -0.06
    .Interface
    -0.06
     Lansing
    -0.06
    .Find
    -0.06
    -med
    -0.06
    Ren
    -0.06
    \Bridge
    -0.06
    POSITIVE LOGITS
    adding
    0.07
     dimensions
    0.06
    ritte
    0.06
     Prometheus
    0.06
     astounding
    0.06
     stunning
    0.06
    cat
    0.06
    heels
    0.06
     pure
    0.06
     ihtiyaç
    0.06
    Activations Density 0.007%

    No Known Activations