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. 21696
    Prev
    Next
    INDEX
    Explanations

    .CodeAnalysis

    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
     závis
    -0.06
     příslu
    -0.06
    .ib
    -0.06
    -inst
    -0.06
    �
    -0.06
    司
    -0.06
    อบ
    -0.06
    idea
    -0.06
    222
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     excuse
    0.08
    .CodeAnalysis
    0.08
     WITHOUT
    0.07
     backlash
    0.07
     showdown
    0.07
     rewarded
    0.07
     групи
    0.06
    ь
    0.06
     CLOSE
    0.06
     ONLY
    0.06
    Activations Density 0.000%

    No Known Activations