© 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. 15-RESID-POST-AA
    11. 63127
    Prev
    Next
    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash

    proper names — tokens that are personal names or user/author names.

    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
        	↵
    -0.07
     nackte
    -0.07
    policy
    -0.06
     برای
    -0.06
    ้↵
    -0.06
     plainly
    -0.06
     eos
    -0.06
    nerRadius
    -0.06
     біль
    -0.06
     factors
    -0.06
    POSITIVE LOGITS
    (components
    0.07
    ("|
    0.07
     unint
    0.06
    _abort
    0.06
    "Don
    0.06
     Dealer
    0.06
    (ob
    0.06
     Duy
    0.06
    door
    0.06
    .gwt
    0.06
    Activations Density 0.025%

    No Known Activations