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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 94734
    Prev
    Next
    INDEX
    Explanations

    Text snippets

    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
    'options
    -0.07
    /sources
    -0.06
     version
    -0.06
    version
    -0.06
     bağlantılar
    -0.06
    dtype
    -0.06
     Jak
    -0.06
    なる
    -0.06
                                  ↵
    -0.06
     meiden
    -0.06
    POSITIVE LOGITS
     выб
    0.07
    删除
    0.07
    .tail
    0.07
    headed
    0.06
     Scient
    0.06
    ामल
    0.06
    ộng
    0.06
     immedi
    0.06
    then
    0.06
    _MP
    0.06
    Activations Density 0.002%

    No Known Activations