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. 19-RESID-POST-AA
    6. 9790
    Prev
    Next
    INDEX
    Explanations

    dollar

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    buffer
    -0.06
     prayer
    -0.06
     především
    -0.06
    .tracks
    -0.06
    ethnic
    -0.06
     pall
    -0.06
     litigation
    -0.06
     Krist
    -0.06
     др
    -0.06
     является
    -0.06
    POSITIVE LOGITS
     Huawei
    0.07
    adoras
    0.06
    ieties
    0.06
    <p
    0.06
     جه
    0.06
     barring
    0.06
     khung
    0.06
     يجب
    0.06
    φ
    0.06
    sm
    0.06
    Activations Density 0.000%

    No Known Activations