© 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. 11-RESID-POST-AA
    11. 20067
    Prev
    Next
    INDEX
    Explanations

    inter

    np_max-act · gemini-2.0-flash

    topics related to leadership and organizational purpose.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _my
    -0.07
    	sign
    -0.06
     packaged
    -0.06
     taste
    -0.06
     pog
    -0.06
    _least
    -0.06
     sugar
    -0.06
     factual
    -0.06
     hood
    -0.06
    .effect
    -0.06
    POSITIVE LOGITS
    _FORM
    0.08
     treadmill
    0.07
    ामग
    0.07
     francais
    0.07
     فرهنگ
    0.06
     AD
    0.06
     trek
    0.06
     администра
    0.06
    τοκ
    0.06
     BAD
    0.06
    Activations Density 0.028%

    No Known Activations