© 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
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 55682
    Prev
    Next
    INDEX
    Explanations

    sprite

    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
    Measurement
    -0.07
     kHz
    -0.07
     недели
    -0.07
     cloudy
    -0.07
     aka
    -0.07
     FM
    -0.06
     پیک
    -0.06
     Buchanan
    -0.06
    定义
    -0.06
     correspondence
    -0.06
    POSITIVE LOGITS
     Sprite
    0.11
     sprite
    0.11
    .sprite
    0.10
    	sprite
    0.10
     sprites
    0.09
    (Sprite
    0.09
    Sprite
    0.08
    sprite
    0.08
    (sprite
    0.08
     特
    0.07
    Activations Density 0.001%

    No Known Activations