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. 111094
    Prev
    Next
    INDEX
    Explanations

    padding

    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
     lời
    -0.07
    ocratic
    -0.07
    柴
    -0.07
    朝
    -0.07
     ammon
    -0.07
     přísluš
    -0.07
     Bolshevik
    -0.07
    -inf
    -0.06
     vessel
    -0.06
     Zoom
    -0.06
    POSITIVE LOGITS
     Ở
    0.07
    '</
    0.06
     Cald
    0.06
     افز
    0.06
    zung
    0.06
    �
    0.06
    ست
    0.06
    clc
    0.06
    ريم
    0.05
    _COMPILE
    0.05
    Activations Density 0.000%

    No Known Activations