© 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. 124995
    Prev
    Next
    INDEX
    Explanations

    Blog posts (early 2000s)

    np_max-act · gemini-2.0-flash

    This neuron recognizes floating-point numbers (decimal values with multiple digits after the period).

    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
    економ
    -0.06
     synaptic
    -0.06
    128
    -0.06
     sein
    -0.06
     Damascus
    -0.06
     effortless
    -0.06
    _Internal
    -0.06
    -lo
    -0.06
     fácil
    -0.06
    orical
    -0.06
    POSITIVE LOGITS
    ++){↵
    0.07
     consideration
    0.07
    AdapterFactory
    0.06
    '}}↵
    0.06
     configFile
    0.06
    _property
    0.06
     Gson
    0.06
    ์↵
    0.06
    ++){↵↵
    0.06
    투
    0.06
    Activations Density 0.002%

    No Known Activations