© 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. 42612
    Prev
    Next
    INDEX
    Explanations

    , and

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect numeric values with decimal points (floating-point numbers).

    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
    _lists
    -0.07
    ]")]↵
    -0.07
    cleanup
    -0.06
     populated
    -0.06
    .High
    -0.06
    	auto
    -0.06
    _bit
    -0.06
     currentIndex
    -0.06
    plural
    -0.06
     browser
    -0.06
    POSITIVE LOGITS
    ificacion
    0.06
    รณ
    0.06
     FEATURE
    0.06
     Крім
    0.06
    班
    0.06
    ротив
    0.06
    Ne
    0.06
    _shell
    0.06
     batchSize
    0.06
     hopping
    0.06
    Activations Density 0.039%

    No Known Activations