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

    Neuronpedia

    APICircuit 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. 54000
    Prev
    Next
    INDEX
    Explanations

    roller

    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
    _PUSH
    -0.07
    แค
    -0.06
    .isNotEmpty
    -0.06
    .getApp
    -0.06
    Born
    -0.06
     gpu
    -0.06
     فرمان
    -0.06
     �
    -0.06
     BCE
    -0.06
     genocide
    -0.06
    POSITIVE LOGITS
    HEY
    0.08
    HERE
    0.07
     courses
    0.07
     REFER
    0.07
     가져
    0.07
    सर
    0.06
     clic
    0.06
     Rotary
    0.06
     recorder
    0.06
     maté
    0.06
    Activations Density 0.002%

    No Known Activations