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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 110680
    Prev
    Next
    INDEX
    Explanations

    file manipulation instructions

    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
    (平成
    -0.07
     Kaf
    -0.07
    consumer
    -0.06
     مشتر
    -0.06
    研究
    -0.06
    极
    -0.06
     Ley
    -0.06
    controls
    -0.06
     리스트
    -0.06
    .cbo
    -0.06
    POSITIVE LOGITS
    (EFFECT
    0.09
     offered
    0.07
    -envelope
    0.07
    SetName
    0.07
    explo
    0.07
    πως
    0.06
    ))*(
    0.06
    ünchen
    0.06
    หลวง
    0.06
     tossed
    0.06
    Activations Density 0.021%

    No Known Activations