© 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. 92548
    Prev
    Next
    INDEX
    Explanations

    studies

    np_max-act · gemini-2.0-flash

    The neuron fires on multi‐token proper names—especially geographic regions or institutions—i.e. it detects named entities like place and organization names.

    oai_token-act-pair · o4-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
     params
    -0.07
    eway
    -0.07
     sales
    -0.06
     broadband
    -0.06
     kodu
    -0.06
     thuộc
    -0.06
     criteria
    -0.06
    /hooks
    -0.06
    (us
    -0.06
    built
    -0.06
    POSITIVE LOGITS
    Equal
    0.07
    　　　　　　　　　　　　　
    0.07
    蛛
    0.06
    WL
    0.06
    	plt
    0.06
     superClass
    0.06
    .ce
    0.05
    RESH
    0.05
    icester
    0.05
    　　　　　　　　　　　　　　
    0.05
    Activations Density 0.039%

    No Known Activations