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. 84281
    Prev
    Next
    INDEX
    Explanations

    Toyota

    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
     hỗn
    -0.07
    (api
    -0.07
    }},↵
    -0.07
     Internet
    -0.06
     chiếu
    -0.06
     خاصة
    -0.06
     网
    -0.06
     関
    -0.06
     ih
    -0.06
     Ин
    -0.06
    POSITIVE LOGITS
    cedes
    0.08
     Chevrolet
    0.08
    OOD
    0.07
    vrolet
    0.07
     poisoned
    0.07
    Conditional
    0.07
    Ford
    0.06
    Records
    0.06
    orna
    0.06
    setItem
    0.06
    Activations Density 0.018%

    No Known Activations