© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 63824
    Prev
    Next
    INDEX
    Explanations

    software

    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
    乱
    -0.07
    *)"
    -0.07
    stantiateViewController
    -0.06
    (Char
    -0.06
     stránky
    -0.06
    泽
    -0.06
     سک
    -0.06
     Administrator
    -0.06
     heavier
    -0.06
     Priority
    -0.06
    POSITIVE LOGITS
     Bannon
    0.06
     Kak
    0.06
     kak
    0.06
    :bg
    0.06
    patial
    0.06
     اللغة
    0.06
     ประเภท
    0.06
     robe
    0.06
     aime
    0.06
     seguro
    0.06
    Activations Density 0.030%

    No Known Activations