Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 3-RESID-POST-AA
    6. 95154
    Prev
    Next
    INDEX
    Explanations

    Jul

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    	main
    -0.08
     much
    -0.07
     front
    -0.07
     basic
    -0.07
     sama
    -0.07
     Head
    -0.07
     general
    -0.07
     více
    -0.07
     common
    -0.07
    	items
    -0.06
    POSITIVE LOGITS
    Jul
    0.35
     Jul
    0.28
     jul
    0.19
    -Jul
    0.17
     JUL
    0.16
     Jun
    0.11
     Julian
    0.11
     Nov
    0.11
     Julia
    0.11
    Jun
    0.11
    Activations Density 0.030%

    No Known Activations