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. 94053
    Prev
    Next
    INDEX
    Explanations

    with

    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
    环
    -0.06
    _Resource
    -0.06
    ramid
    -0.06
    nodiscard
    -0.06
    -aut
    -0.06
     نور
    -0.06
    ActionButton
    -0.06
    Speech
    -0.06
    acidad
    -0.05
     QDom
    -0.05
    POSITIVE LOGITS
     당시
    0.07
     Batt
    0.07
    _cliente
    0.06
     Omni
    0.06
    adresse
    0.06
     باشید
    0.06
     EVP
    0.06
    оді
    0.06
    _Show
    0.06
    -AA
    0.06
    Activations Density 0.012%

    No Known Activations