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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 11-RESID-POST-AA
    6. 100016
    Prev
    Next
    INDEX
    Explanations

    context

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Starr
    -0.07
    一緒
    -0.07
     papers
    -0.07
    .Find
    -0.07
     dữ
    -0.07
     nhạc
    -0.06
    lenme
    -0.06
     foam
    -0.06
     Chase
    -0.06
    blings
    -0.06
    POSITIVE LOGITS
     iParam
    0.07
     Elasticsearch
    0.06
     데이터
    0.06
     inlet
    0.06
     engine
    0.06
    情况
    0.06
     inclus
    0.06
     EntryPoint
    0.06
    ingga
    0.06
     визначення
    0.06
    Activations Density 0.008%

    No Known Activations