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. 11-RESID-POST-AA
    6. 123668
    Prev
    Next
    INDEX
    Explanations

    elevation

    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
     lifespan
    -0.07
    CompanyId
    -0.07
    _sa
    -0.06
    できる
    -0.06
     ELF
    -0.06
    insi
    -0.06
     pudding
    -0.06
    ANA
    -0.06
     sním
    -0.06
     usability
    -0.06
    POSITIVE LOGITS
     운동
    0.07
    .Groups
    0.07
    (rc
    0.07
    ->$
    0.06
     vergi
    0.06
     Plugins
    0.06
    office
    0.06
    (sub
    0.06
     wished
    0.06
    ???
    0.06
    Activations Density 0.006%

    No Known Activations