© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 41550
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    The neuron detects discourse‐level transition words or connectives (e.g. “and,” “for,” “here,” “is,” “the”) that introduce examples or explanations.

    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
     zwarte
    -0.07
     corrobor
    -0.07
     ini
    -0.06
    .mu
    -0.06
     keine
    -0.06
     blat
    -0.06
     دن
    -0.06
    альну
    -0.06
    -ad
    -0.06
     рев
    -0.06
    POSITIVE LOGITS
    radio
    0.07
    提出
    0.06
    	
    ↵	
    ↵
    0.06
     FL
    0.06
    )*/↵
    0.06
    /operators
    0.06
    正确
    0.06
     Lif
    0.06
     půl
    0.06
     Residence
    0.06
    Activations Density 0.002%

    No Known Activations