© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30008
    Prev
    Next
    INDEX
    Explanations

    both

    np_max-act · gemini-2.0-flash

    The neuron fires on words that introduce or describe the makeup or structure of something (e.g. forming a, based on, both … and …, narrative, vignettes).

    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
    	ctrl
    -0.07
    txt
    -0.07
    match
    -0.07
    اكم
    -0.06
    -ind
    -0.06
    aceous
    -0.06
     six
    -0.06
    κέ
    -0.06
     mediante
    -0.06
     noise
    -0.06
    POSITIVE LOGITS
     Daemon
    0.06
     isSelected
    0.06
    MEMORY
    0.06
    บาย
    0.06
     caution
    0.06
     겨
    0.06
    _languages
    0.06
    _based
    0.06
     прик
    0.06
     Hydraulic
    0.06
    Activations Density 0.753%

    No Known Activations