© 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. 44167
    Prev
    Next
    INDEX
    Explanations

    unicode

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on occurrences of the word “Unicode” (e.g. in copyright headers or include paths) in source‐file boilerplate.

    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
    (include
    -0.07
    (job
    -0.06
    CLUS
    -0.06
    ็นต
    -0.06
     ف
    -0.06
    ibrated
    -0.06
     종
    -0.06
     Quy
    -0.06
    day
    -0.06
    _checkout
    -0.06
    POSITIVE LOGITS
     yapılacak
    0.07
     jpeg
    0.07
    	eval
    0.07
     های
    0.07
    Emitter
    0.07
    áky
    0.07
     drainage
    0.07
    raphics
    0.06
     tutorials
    0.06
    .defaultProps
    0.06
    Activations Density 0.007%

    No Known Activations