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. 19302
    Prev
    Next
    INDEX
    Explanations

    R

    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
    lijah
    -0.07
     Hampton
    -0.06
     Instrument
    -0.06
    adopt
    -0.06
    rength
    -0.06
    vrier
    -0.06
    utorials
    -0.06
     душ
    -0.06
     PARAM
    -0.06
     якій
    -0.06
    POSITIVE LOGITS
    _SLAVE
    0.07
    ۱۶
    0.07
    isiert
    0.06
     lỗi
    0.06
    菜
    0.06
    ано
    0.06
    대의
    0.06
     �
    0.06
     goede
    0.06
    -percent
    0.06
    Activations Density 0.445%

    No Known Activations