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. 7-RESID-POST-AA
    6. 72416
    Prev
    Next
    INDEX
    Explanations

    trans

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    evi
    -0.07
     طرف
    -0.06
    paste
    -0.06
     Capital
    -0.06
     chief
    -0.06
     tantra
    -0.06
    osopher
    -0.06
    ene
    -0.06
    grant
    -0.06
     uncon
    -0.06
    POSITIVE LOGITS
     Ebay
    0.06
    .DEFINE
    0.06
    �
    0.06
     fft
    0.06
    ?[
    0.05
    pairs
    0.05
    ╝
    0.05
     บาง
    0.05
     lucky
    0.05
    �
    0.05
    Activations Density 0.011%

    No Known Activations