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. 11-RESID-POST-AA
    6. 961
    Prev
    Next
    INDEX
    Explanations

    school

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the phrase “high school,” especially when it appears as part of a headline or proper‐noun label.

    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
     Root
    -0.07
    Root
    -0.06
     funct
    -0.06
     Blue
    -0.06
    蓝
    -0.06
    'na
    -0.06
     getSize
    -0.06
     ()=>
    -0.06
    Leaf
    -0.06
    .Sdk
    -0.06
    POSITIVE LOGITS
     합
    0.08
     HS
    0.07
     вспом
    0.07
    高校
    0.07
    ManyToOne
    0.07
     듣
    0.07
     presidential
    0.06
    signed
    0.06
    fections
    0.06
    	hs
    0.06
    Activations Density 0.006%

    No Known Activations