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. 7-RESID-POST-AA
    6. 108880
    Prev
    Next
    INDEX
    Explanations

    p

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unveiled
    -0.07
     "../../../../
    -0.07
    าณ
    -0.07
    _off
    -0.06
    ιστη
    -0.06
     εκεί
    -0.06
     เท
    -0.06
    .middleware
    -0.06
     comerc
    -0.06
    خت
    -0.06
    POSITIVE LOGITS
     p
    0.08
    p
    0.08
    )p
    0.07
    div
    0.06
     دفاع
    0.06
    іп
    0.06
     yapı
    0.06
    APA
    0.06
    <p
    0.06
     dumpsters
    0.06
    Activations Density 0.007%

    No Known Activations