Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 15-RESID-POST-AA
    6. 53838
    Prev
    Next
    INDEX
    Explanations

    1

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dog
    -0.07
     wlan
    -0.06
    ◆
    -0.06
    itary
    -0.06
    PE
    -0.06
    Dry
    -0.06
    ANTI
    -0.06
    :c
    -0.06
    .bb
    -0.06
    ecta
    -0.06
    POSITIVE LOGITS
    같은
    0.08
    (txt
    0.07
    /license
    0.07
     kans
    0.07
     Colt
    0.07
    (resp
    0.07
    觀
    0.07
     awesome
    0.07
     چگونه
    0.07
    Await
    0.07
    Activations Density 0.000%

    No Known Activations