© 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. 15-RESID-POST-AA
    11. 57318
    Prev
    Next
    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash

    It detects phrases that introduce or signal a forthcoming list of items, tips, or examples.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    .AD
    -0.07
     bola
    -0.06
     Brexit
    -0.06
     Essentials
    -0.06
    	wx
    -0.06
     Bengals
    -0.06
     TextArea
    -0.06
    ("/");↵
    -0.06
     لف
    -0.06
     compound
    -0.06
    POSITIVE LOGITS
    ebilirsiniz
    0.07
    aines
    0.07
    ườ
    0.07
    ่อย
    0.07
    collection
    0.07
    PostalCodes
    0.07
     payday
    0.06
    xEB
    0.06
    -names
    0.06
    ramids
    0.06
    Activations Density 0.017%

    No Known Activations