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. 54004
    Prev
    Next
    INDEX
    Explanations

    references and links

    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
    Fee
    -0.08
     transitioning
    -0.07
    _sources
    -0.07
    hani
    -0.07
    Registration
    -0.06
    Directory
    -0.06
    >T
    -0.06
     rolled
    -0.06
     будинку
    -0.06
    ipl
    -0.06
    POSITIVE LOGITS
    writer
    0.06
    ابات
    0.06
    ель
    0.06
     submitted
    0.05
    -rec
    0.05
    发生
    0.05
    ervatives
    0.05
    _Id
    0.05
    United
    0.05
     United
    0.05
    Activations Density 0.000%

    No Known Activations