© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 109896
    Prev
    Next
    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash

    The neuron activates on common list‐continuation or “and so on” discourse markers (e.g. “and so on,” “and so forth,” “etc.”) that signal enumeration or example extension.

    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
    İY
    -0.07
    Brush
    -0.07
    eel
    -0.07
    elic
    -0.07
     грун
    -0.07
     quý
    -0.07
    }','
    -0.06
    ců
    -0.06
     CEL
    -0.06
     Diy
    -0.06
    POSITIVE LOGITS
     Sokol
    0.07
     acab
    0.06
     Enabled
    0.06
     Pont
    0.06
     assured
    0.06
     onClose
    0.06
    '.$
    0.06
     Mourinho
    0.06
     contrib
    0.06
     사무
    0.06
    Activations Density 0.025%

    No Known Activations