© 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. 30606
    Prev
    Next
    INDEX
    Explanations

    source code

    np_max-act · gemini-2.0-flash

    The neuron fires on attribute assignments in markup, i.e. tokens like name=" indicating the start of an XML/HTML attribute value.

    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
     IOCTL
    -0.07
    ิพ
    -0.07
     Connectivity
    -0.07
     contingency
    -0.07
    zoom
    -0.06
    <GameObject
    -0.06
    	Grid
    -0.06
     isAuthenticated
    -0.06
     查
    -0.06
     Entries
    -0.06
    POSITIVE LOGITS
    %%
    0.06
     Boise
    0.06
    _tpl
    0.06
     návr
    0.06
    ψει
    0.06
     Predictor
    0.06
    bg
    0.06
     Meetings
    0.06
    ucker
    0.06
    -European
    0.05
    Activations Density 0.024%

    No Known Activations