© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 104746
    Prev
    Next
    INDEX
    Explanations

    cluster

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of astronomical “clusters,” especially the word cluster(s) (often in the context of galaxy clusters or specific cluster names).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    aspects related to the physical properties and dynamics of galaxy clusters.

    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
    adí
    -0.07
     Bulldogs
    -0.07
    Decoder
    -0.06
     Sho
    -0.06
    .setTextSize
    -0.06
    事情
    -0.06
     stomach
    -0.06
     Writer
    -0.06
     Ну
    -0.06
     Jimmy
    -0.06
    POSITIVE LOGITS
    asyarak
    0.07
    λο
    0.06
    -project
    0.06
    neh
    0.06
    ()-
    0.06
    (TypeError
    0.06
     Floyd
    0.06
     town
    0.06
     =~
    0.06
    	tree
    0.06
    Activations Density 0.002%

    No Known Activations