© 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. 129779
    Prev
    Next
    INDEX
    Explanations

    instructions or suggestions

    np_max-act · gemini-2.0-flash

    This neuron activates on instructional action verbs that start procedural steps (e.g., “Define,” “Establish,” “Develop,” “Secure,” “Launch,” “Monitor,” “Disseminate”).

    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
    .B
    -0.07
     zijn
    -0.07
    YYY
    -0.07
     května
    -0.06
    片
    -0.06
    *b
    -0.06
     ولي
    -0.06
    (ft
    -0.06
    -No
    -0.06
     Amid
    -0.06
    POSITIVE LOGITS
    	progress
    0.06
     gym
    0.06
     Electronic
    0.06
     اق
    0.06
    _accum
    0.06
     extern
    0.06
     відч
    0.06
    didn
    0.06
    milliseconds
    0.06
    _cur
    0.06
    Activations Density 0.116%

    No Known Activations