© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 44534
    Prev
    Next
    INDEX
    Explanations

    article snippets

    np_max-act · gemini-2.0-flash

    This neuron detects promotional key-fact phrases—especially numerical service details and highlights—such as “Open 24/7” or “Important touristic center of the country.”

    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
    dy
    -0.07
     AWS
    -0.07
    .removeAll
    -0.06
     checkpoints
    -0.06
     lam
    -0.06
     drv
    -0.06
     aluminium
    -0.06
    }`↵
    -0.06
     Adult
    -0.06
     multiples
    -0.06
    POSITIVE LOGITS
     říj
    0.07
     hinder
    0.06
     internationally
    0.06
     bound
    0.06
     Angiosper
    0.06
    =find
    0.06
    ausal
    0.06
    _assigned
    0.06
     readOnly
    0.06
    νώ
    0.06
    Activations Density 0.118%

    No Known Activations