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. 93549
    Prev
    Next
    INDEX
    Explanations

    Judge

    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
    하여
    -0.07
     komen
    -0.06
    Scan
    -0.06
    责任
    -0.06
    MB
    -0.06
    OLTIP
    -0.06
     bamb
    -0.06
    ्यवस
    -0.06
    اورزی
    -0.06
    petto
    -0.06
    POSITIVE LOGITS
    Tech
    0.06
    .Topic
    0.06
    (required
    0.06
     lakh
    0.06
    ΗΣ
    0.06
     Gut
    0.06
    licas
    0.06
    .socket
    0.06
    مع
    0.06
     Rath
    0.06
    Activations Density 0.002%

    No Known Activations