© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 30799
    Prev
    Next
    INDEX
    Explanations

    stages and phases

    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
     Burning
    -0.08
     broker
    -0.07
    closing
    -0.07
    817
    -0.07
    킨
    -0.06
     eccentric
    -0.06
    Channels
    -0.06
    Judge
    -0.06
    物理
    -0.06
    uld
    -0.06
    POSITIVE LOGITS
     دقیق
    0.07
     кисл
    0.07
     $('#'
    0.06
     experimentation
    0.06
    .Total
    0.06
    �
    0.06
    	cm
    0.06
     attempted
    0.06
     섬
    0.06
     Сред
    0.06
    Activations Density 0.215%

    No Known Activations