© 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. 11-RESID-POST-AA
    11. 89131
    Prev
    Next
    INDEX
    Explanations

    Code and data snippets

    np_max-act · gemini-2.0-flash

    details about vehicle specifications and configurations.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on special control and formatting tokens (e.g. `<|begin_of_text|>`, `<|start_header_id|>`, `<|end_header_id|>`, etc.). It’s essentially detecting the metadata and markup tokens used to structure the prompt.

    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
    olah
    -0.06
    dan
    -0.06
     suit
    -0.06
     пару
    -0.06
    weeted
    -0.06
    apest
    -0.06
    vert
    -0.06
    .mit
    -0.06
    θήκη
    -0.06
    alyze
    -0.06
    POSITIVE LOGITS
     gql
    0.08
    	label
    0.07
    启动
    0.07
    ¹
    0.07
     ",
    0.07
     UIColor
    0.07
    	yy
    0.07
    toLocale
    0.07
    ्सर
    0.07
     mouseY
    0.06
    Activations Density 0.034%

    No Known Activations