© 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. 44403
    Prev
    Next
    INDEX
    Explanations

    new or latest

    np_max-act · gemini-2.0-flash

    The neuron lights up on the main content words in a search query (e.g. topical or temporal keywords like “latest,” “budget,” “art,” “on”), effectively picking out the key informative terms.

    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
     forex
    -0.07
    StringUtil
    -0.07
     Another
    -0.07
    =tmp
    -0.07
    游
    -0.06
     objectForKey
    -0.06
    FAILURE
    -0.06
     عليها
    -0.06
     plainly
    -0.06
    actual
    -0.06
    POSITIVE LOGITS
    nelly
    0.07
    (-
    0.06
     MP
    0.06
    .sources
    0.06
     baud
    0.06
     Chic
    0.06
     watt
    0.06
     dic
    0.06
    inos
    0.06
     chrono
    0.06
    Activations Density 0.000%

    No Known Activations